#=SOURCE=# https://ossci-raw-job-status.s3.amazonaws.com/log/91075863282
2026-07-31T06:23:20.5556580Z Running test_torch_config_hash_determinism 1/1 ... [2026-07-31 06:23:20.555422][413240.7723005]
2026-07-31T06:23:20.5557620Z SCRIBE_GRAPHQL_ACCESS_TOKEN is NOT set
2026-07-31T06:23:20.5560210Z Executing ['/Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466/bin/python', '-bb', 'test_torch_config_hash_determinism.py', '-m', '(not serial)', '--shard-id=1', '--num-shards=1', '-v', '-vv', '-rfEX', '-p', 'no:xdist', '--use-pytest', '-x', '--reruns=2', '--import-slow-tests', '--import-disabled-tests'] ... [2026-07-31 06:23:20.555730]
2026-07-31T06:23:22.7658640Z 
2026-07-31T06:23:22.7760630Z test_torch_config_hash_determinism 1/1 was successful, full logs can be found in artifacts with path test/test-reports/test_torch_config_hash_determinism_1.1_4894102e0c1c4334_.log
2026-07-31T06:23:22.7862330Z Running 3 items in this shard: test/test_torch_config_hash_determinism.py::TestConfigModule::test_basic_detection, test/test_torch_config_hash_determinism.py::TestConfigModule::test_inductor_config_hash_portable_deterministic, test/test_torch_config_hash_determinism.py::TestConfigModule::test_inductor_config_hash_portable_without_ignore
2026-07-31T06:23:22.7962690Z 
2026-07-31T06:23:22.8065080Z Finished test_torch_config_hash_determinism 1/1 ... [2026-07-31 06:23:22.765985][413242.982887416], took 0.04min
2026-07-31T06:23:23.0801330Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_torch_config_hash_determinism/test_torch_config_hash_determinism-e674ac6ef6a9bcdd.xml
2026-07-31T06:23:24.3940380Z Running test_torchfuzz_repros 1/1 ... [2026-07-31 06:23:24.393845][413244.610766375]
2026-07-31T06:23:24.3941380Z SCRIBE_GRAPHQL_ACCESS_TOKEN is NOT set
2026-07-31T06:23:24.3943860Z Executing ['/Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466/bin/python', '-bb', 'test_torchfuzz_repros.py', '-m', '(not serial)', '--shard-id=1', '--num-shards=1', '-v', '-vv', '-rfEX', '-p', 'no:xdist', '--use-pytest', '-x', '--reruns=2', '--import-slow-tests', '--import-disabled-tests'] ... [2026-07-31 06:23:24.394161]
2026-07-31T06:23:26.8314580Z 
2026-07-31T06:23:26.8315500Z test_torchfuzz_repros 1/1 was successful, full logs can be found in artifacts with path test/test-reports/test_torchfuzz_repros_1.1_bd0ce6645ada9dab_.log
2026-07-31T06:23:26.8317620Z Running 6 items in this shard: test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_163894, test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_164157, test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_164185, test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_164428_already_exists, test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_164484, test/test_torchfuzz_repros.py::TestFuzzerCompileIssues::test_fuzzer_issue_164486
2026-07-31T06:23:26.8319140Z 
2026-07-31T06:23:26.8319370Z Finished test_torchfuzz_repros 1/1 ... [2026-07-31 06:23:26.831568][413247.048516333], took 0.04min
2026-07-31T06:23:27.2394540Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_torchfuzz_repros/test_torchfuzz_repros-9147a3fcc9a8ad32.xml
2026-07-31T06:23:28.6021480Z Running test_transformers 1/2 ... [2026-07-31 06:23:28.601898][413248.818865041]
2026-07-31T06:23:28.6022430Z SCRIBE_GRAPHQL_ACCESS_TOKEN is NOT set
2026-07-31T06:23:28.6024870Z Executing ['/Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466/bin/python', '-bb', 'test_transformers.py', '-m', '(not serial)', '--shard-id=1', '--num-shards=2', '-v', '-vv', '-rfEX', '-p', 'no:xdist', '--use-pytest', '-x', '--reruns=2', '--import-slow-tests', '--import-disabled-tests'] ... [2026-07-31 06:23:28.602258]
2026-07-31T06:23:29.2230150Z 
2026-07-31T06:23:29.2374010Z test_sympy_utils 1/1 was successful, full logs can be found in artifacts with path test/test-reports/test_sympy_utils_1.1_8f606ec86f4cfec2_.log
2026-07-31T06:23:29.2700430Z Running 235 items in this shard: test/test_sympy_utils.py::TestNumbers::test_float_cast, test/test_sympy_utils.py::TestNumbers::test_int_infinity, test/test_sympy_utils.py::TestNumbers::test_lt_self, test/test_sympy_utils.py::TestNumbers::test_mixed_oo_int_oo, test/test_sympy_utils.py::TestNumbers::test_relation, test/test_sympy_utils.py::TestCppPrinter::test_min_max_preserve_float_expressions, test/test_sympy_utils.py::TestCppPrinter::test_min_max_preserve_integer_expressions, test/test_sympy_utils.py::TestValueRanges::test_binary_bool_ref_range_fn_and_, test/test_sympy_utils.py::TestValueRanges::test_binary_bool_ref_range_fn_bitwise_and, test/test_sympy_utils.py::TestValueRanges::test_binary_bool_ref_range_fn_bitwise_or, test/test_sympy_utils.py::TestValueRanges::test_binary_bool_ref_range_fn_bitwise_xor, test/test_sympy_utils.py::TestValueRanges::test_binary_bool_ref_range_fn_or_, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_add_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_add_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_and_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_and_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_or_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_or_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_xor_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_bitwise_xor_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_floordiv_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_floordiv_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_maximum_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_maximum_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_minimum_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_minimum_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_mod_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_mod_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_mul_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_mul_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_pow_by_natural_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_pow_by_natural_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_pow_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_pow_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_sub_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_sub_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_truediv_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_fn_truediv_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_add, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_bitwise_and, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_bitwise_or, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_bitwise_xor, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_eq, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_floordiv, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_ge, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_gt, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_le, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_lt, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_maximum, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_minimum, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_mod, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_mul, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_ne, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_pow, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_pow_by_natural, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_sub, test/test_sympy_utils.py::TestValueRanges::test_binary_ref_range_fn_truediv, test/test_sympy_utils.py::TestValueRanges::test_bitwise_ref_range_fn_bitwise_and, test/test_sympy_utils.py::TestValueRanges::test_bitwise_ref_range_fn_bitwise_or, test/test_sympy_utils.py::TestValueRanges::test_bitwise_ref_range_fn_bitwise_xor, test/test_sympy_utils.py::TestValueRanges::test_bool_minimum_maximum, test/test_sympy_utils.py::TestValueRanges::test_bool_minimum_maximum_mixed_raises, test/test_sympy_utils.py::TestValueRanges::test_bound_sympy_mod_subtraction, test/test_sympy_utils.py::TestValueRanges::test_bound_sympy_negative_pow, test/test_sympy_utils.py::TestValueRanges::test_bound_sympy_python_mod_subtraction_negative_base, test/test_sympy_utils.py::TestValueRanges::test_mul_zero_unknown, test/test_sympy_utils.py::TestValueRanges::test_pow_half, test/test_sympy_utils.py::TestValueRanges::test_python_mod, test/test_sympy_utils.py::TestValueRanges::test_trunc_infinite, test/test_sympy_utils.py::TestValueRanges::test_unary_bool_ref_range_fn_not_, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_abs_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_abs_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_ceil_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_ceil_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_exp_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_exp_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_floor_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_floor_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_log_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_log_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_neg_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_neg_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_reciprocal_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_reciprocal_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_sqrt_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_sqrt_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_square_dtype_float, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_fn_square_dtype_int, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_abs, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_ceil, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_exp, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_floor, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_log, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_neg, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_reciprocal, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_sqrt, test/test_sympy_utils.py::TestValueRanges::test_unary_ref_range_fn_square, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_abs, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_add, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_and_, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_bitwise_and, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_bitwise_or, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_bitwise_xor, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_ceil, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_eq, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_exp, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_floor, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_floordiv, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_ge, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_gt, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_le, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_log, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_lt, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_maximum, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_minimum, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_mod, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_mul, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_ne, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_neg, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_not_, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_or_, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_pow, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_pow_by_natural, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_reciprocal, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_sqrt, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_square, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_sub, test/test_sympy_utils.py::TestSympyInterp::test_interp_fn_truediv, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_abs, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_add, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_and_, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_bitwise_and, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_bitwise_or, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_bitwise_xor, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_ceil, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_eq, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_exp, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_floor, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_floordiv, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_ge, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_gt, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_le, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_log, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_lt, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_maximum, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_minimum, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_mod, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_mul, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_ne, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_neg, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_not_, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_or_, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_pow, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_pow_by_natural, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_reciprocal, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_sqrt, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_square, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_sub, test/test_sympy_utils.py::TestSympyInterp::test_python_interp_fx_fn_truediv, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_abs, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_add, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_and_, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_bitwise_and, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_bitwise_or, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_bitwise_xor, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_ceil, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_eq, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_exp, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_floor, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_floordiv, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_ge, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_gt, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_le, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_log, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_lt, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_maximum, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_minimum, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_mod, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_mul, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_ne, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_neg, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_not_, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_or_, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_pow, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_pow_by_natural, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_reciprocal, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_sqrt, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_square, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_sub, test/test_sympy_utils.py::TestSympyInterp::test_tensor_interp_fn_truediv, test/test_sympy_utils.py::TestSympySolve::test_addition, test/test_sympy_utils.py::TestSympySolve::test_floordiv_Equality, test/test_sympy_utils.py::TestSympySolve::test_floordiv_GreaterThan, test/test_sympy_utils.py::TestSympySolve::test_floordiv_LessThan, test/test_sympy_utils.py::TestSympySolve::test_floordiv_StrictGreaterThan, test/test_sympy_utils.py::TestSympySolve::test_floordiv_StrictLessThan, test/test_sympy_utils.py::TestSympySolve::test_floordiv_Unequality, test/test_sympy_utils.py::TestSympySolve::test_floordiv_eq_simplify, test/test_sympy_utils.py::TestSympySolve::test_give_up, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_Equality, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_Unequality, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_inequality_GreaterThan, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_inequality_LessThan, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_inequality_StrictGreaterThan, test/test_sympy_utils.py::TestSympySolve::test_multiplication_division_inequality_StrictLessThan, test/test_sympy_utils.py::TestSympySolve::test_noop_Equality, test/test_sympy_utils.py::TestSympySolve::test_noop_GreaterThan, test/test_sympy_utils.py::TestSympySolve::test_noop_LessThan, test/test_sympy_utils.py::TestSympySolve::test_noop_StrictGreaterThan, test/test_sympy_utils.py::TestSympySolve::test_noop_StrictLessThan, test/test_sympy_utils.py::TestSympySolve::test_noop_Unequality, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_Equality, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_GreaterThan, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_LessThan, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_StrictGreaterThan, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_StrictLessThan, test/test_sympy_utils.py::TestSympySolve::test_noop_rhs_Unequality, test/test_sympy_utils.py::TestSympySolve::test_simple_floordiv_gcd, test/test_sympy_utils.py::TestSympySolve::test_z3_proof_floordiv_eq_simplify, test/test_sympy_utils.py::TestSympyFunctions::test_min_max_scaled_known_sign_term, test/test_sympy_utils.py::TestSympyFunctions::test_modular_indexing_does_not_strip_unproven_nonnegative_term, test/test_sympy_utils.py::TestSympyFunctions::test_pickle, test/test_sympy_utils.py::TestSympyFunctions::test_shift_edges, test/test_sympy_utils.py::TestSingletonInt::test_basic, test/test_sympy_utils.py::TestIdentity::test_cast_identity_float, test/test_sympy_utils.py::TestIdentity::test_cast_identity_illegal, test/test_sympy_utils.py::TestIdentity::test_cast_identity_int, test/test_sympy_utils.py::TestIdentity::test_expand_identity, test/test_sympy_utils.py::TestTypedExpr::test_typed_expr, test/test_sympy_utils.py::TestCCodePrinting::test_ccode_in_compound_expr, test/test_sympy_utils.py::TestCCodePrinting::test_ceil_to_int_ccode, test/test_sympy_utils.py::TestCCodePrinting::test_floor_to_int_ccode, test/test_sympy_utils.py::TestCCodePrinting::test_floor_to_int_ccode_compound, test/test_sympy_utils.py::TestCCodePrinting::test_to_float_ccode, test/test_sympy_utils.py::TestCCodePrinting::test_trunc_to_int_ccode
2026-07-31T06:23:29.2745700Z 
2026-07-31T06:23:29.2745930Z Finished test_sympy_utils 1/1 ... [2026-07-31 06:23:29.210198][413249.427173583], took 0.31min
2026-07-31T06:23:29.5925480Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_sympy_utils/test_sympy_utils-c7e0b468146bffe5.xml
2026-07-31T06:23:30.8878610Z Running test_varlen_attention 1/1 ... [2026-07-31 06:23:30.887658][413251.104648666]
2026-07-31T06:23:30.8879100Z SCRIBE_GRAPHQL_ACCESS_TOKEN is NOT set
2026-07-31T06:23:30.8881240Z Executing ['/Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466/bin/python', '-bb', 'test_varlen_attention.py', '-m', '(not serial)', '--shard-id=1', '--num-shards=1', '-v', '-vv', '-rfEX', '-p', 'no:xdist', '--use-pytest', '-x', '--reruns=2', '--import-slow-tests', '--import-disabled-tests'] ... [2026-07-31 06:23:30.888003]
2026-07-31T06:23:33.2713840Z 
2026-07-31T06:23:33.2715090Z test_varlen_attention 1/1 was successful, full logs can be found in artifacts with path test/test-reports/test_varlen_attention_1.1_d9a4ee6a600f766d_.log
2026-07-31T06:23:33.2715690Z Running 0 items in this shard:
2026-07-31T06:23:33.2715830Z 
2026-07-31T06:23:33.2716050Z Finished test_varlen_attention 1/1 ... [2026-07-31 06:23:33.271519][413253.488539208], took 0.04min
2026-07-31T06:23:33.6093400Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_varlen_attention/test_varlen_attention-a2335532184d9399.xml
2026-07-31T06:23:34.9051910Z Running xpu/test_gemm 1/1 ... [2026-07-31 06:23:34.905020][413255.122062125]
2026-07-31T06:23:34.9052280Z SCRIBE_GRAPHQL_ACCESS_TOKEN is NOT set
2026-07-31T06:23:34.9054330Z Executing ['/Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466/bin/python', '-bb', 'xpu/test_gemm.py', '-m', '(not serial)', '--shard-id=1', '--num-shards=1', '-v', '-vv', '-rfEX', '-p', 'no:xdist', '--use-pytest', '-x', '--reruns=2', '--import-slow-tests', '--import-disabled-tests'] ... [2026-07-31 06:23:34.905305]
2026-07-31T06:23:37.2362690Z 
2026-07-31T06:23:37.2363700Z xpu/test_gemm 1/1 was successful, full logs can be found in artifacts with path test/test-reports/xpu.test_gemm_1.1_a1f62774d35a0edc_.log
2026-07-31T06:23:37.2364250Z Running 0 items in this shard:
2026-07-31T06:23:37.2364390Z 
2026-07-31T06:23:37.2364590Z Finished xpu/test_gemm 1/1 ... [2026-07-31 06:23:37.236338][413257.453406458], took 0.04min
2026-07-31T06:23:37.5581720Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/xpu.test_gemm/xpu.test_gemm-fcf61c3bc9671a5b.xml
2026-07-31T06:23:37.5583420Z GITHUB_RUN_ID, GITHUB_RUN_ATTEMPT, or ARTIFACTS_FILE_SUFFIX not set, not uploading
2026-07-31T06:23:37.5583800Z Uploading artifacts took 0.00 seconds
2026-07-31T06:23:48.4474510Z 
2026-07-31T06:23:48.4475360Z test_testing 1/1 was successful, full logs can be found in artifacts with path test/test-reports/test_testing_1.1_d90ba40d0db6c9d0_.log
2026-07-31T06:23:48.5100820Z Running 2097 items in this shard: test/test_testing.py::TestTestingCPU::test_assertEqual_longMessage_cpu, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_bool, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_complex128, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_complex64, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_float16, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_float32, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_float64, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_int16, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_int32, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_int64, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_int8, test/test_testing.py::TestTestingCPU::test_assertEqual_numpy_cpu_uint8, test/test_testing.py::TestTestingCPU::test_callable_msg_cpu, test/test_testing.py::TestTestingCPU::test_cuda_assert_should_not_stop_common_distributed_test_suite_cpu, test/test_testing.py::TestTestingCPU::test_cuda_assert_should_stop_common_device_type_test_suite_cpu, test/test_testing.py::TestTestingCPU::test_cuda_assert_should_stop_common_utils_test_suite_cpu, test/test_testing.py::TestTestingCPU::test_get_supported_dtypes_cpu, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_bool, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_float16, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_float32, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_float64, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_int16, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_int32, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_int64, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_int8, test/test_testing.py::TestTestingCPU::test_isclose_atol_rtol_greater_than_zero_cpu_uint8, test/test_testing.py::TestTestingCPU::test_isclose_bool_cpu, test/test_testing.py::TestTestingCPU::test_isclose_complex_cpu_complex128, test/test_testing.py::TestTestingCPU::test_isclose_complex_cpu_complex64, test/test_testing.py::TestTestingCPU::test_isclose_equal_nan_broadcast_cpu_float16, test/test_testing.py::TestTestingCPU::test_isclose_equal_nan_broadcast_cpu_float32, test/test_testing.py::TestTestingCPU::test_isclose_equality_shortcut_cpu, test/test_testing.py::TestTestingCPU::test_isclose_float_cpu_float16, test/test_testing.py::TestTestingCPU::test_isclose_float_cpu_float32, test/test_testing.py::TestTestingCPU::test_isclose_float_cpu_float64, test/test_testing.py::TestTestingCPU::test_isclose_integer_cpu_int16, test/test_testing.py::TestTestingCPU::test_isclose_integer_cpu_int32, test/test_testing.py::TestTestingCPU::test_isclose_integer_cpu_int64, test/test_testing.py::TestTestingCPU::test_isclose_integer_cpu_int8, test/test_testing.py::TestTestingCPU::test_isclose_integer_cpu_uint8, test/test_testing.py::TestTestingCPU::test_isclose_nan_equality_shortcut_cpu_complex128, test/test_testing.py::TestTestingCPU::test_isclose_nan_equality_shortcut_cpu_complex64, test/test_testing.py::TestTestingCPU::test_isclose_nan_equality_shortcut_cpu_float16, test/test_testing.py::TestTestingCPU::test_isclose_nan_equality_shortcut_cpu_float32, test/test_testing.py::TestTestingCPU::test_isclose_nan_equality_shortcut_cpu_float64, test/test_testing.py::TestTestingCPU::test_setup_and_teardown_run_for_device_specific_tests_cpu, test/test_testing.py::TestTestingCPU::test_supported_dtypes_abs_cpu, test/test_testing.py::TestFrameworkUtils::test_filtering_env_var, test/test_testing.py::TestEnvironmentDefFlag::test_default_true_explicit_zero_overrides_implication, test/test_testing.py::TestEnvironmentDefFlag::test_explicit_one_with_no_implication, test/test_testing.py::TestEnvironmentDefFlag::test_explicit_zero_overrides_implication, test/test_testing.py::TestEnvironmentDefFlag::test_unset_with_implication_false, test/test_testing.py::TestEnvironmentDefFlag::test_unset_with_implication_true, test/test_testing.py::TestAssertClose::test_bool, test/test_testing.py::TestAssertClose::test_default_tolerance_selection_mismatching_dtypes, test/test_testing.py::TestAssertClose::test_docstring_examples, test/test_testing.py::TestAssertClose::test_matching, test/test_testing.py::TestAssertClose::test_matching_atol, test/test_testing.py::TestAssertClose::test_matching_conjugate_bit, test/test_testing.py::TestAssertClose::test_matching_nan, test/test_testing.py::TestAssertClose::test_matching_nan_with_equal_nan, test/test_testing.py::TestAssertClose::test_matching_rtol, test/test_testing.py::TestAssertClose::test_meta, test/test_testing.py::TestAssertClose::test_mismatching_dtype, test/test_testing.py::TestAssertClose::test_mismatching_dtype_no_check, test/test_testing.py::TestAssertClose::test_mismatching_layout, test/test_testing.py::TestAssertClose::test_mismatching_layout_no_check, test/test_testing.py::TestAssertClose::test_mismatching_shape, test/test_testing.py::TestAssertClose::test_mismatching_stride, test/test_testing.py::TestAssertClose::test_mismatching_stride_no_check, test/test_testing.py::TestAssertClose::test_mismatching_types, test/test_testing.py::TestAssertClose::test_mismatching_types_subclasses, test/test_testing.py::TestAssertClose::test_mismatching_types_type_equality, test/test_testing.py::TestAssertClose::test_mismatching_values, test/test_testing.py::TestAssertClose::test_mismatching_values_atol, test/test_testing.py::TestAssertClose::test_mismatching_values_rtol, test/test_testing.py::TestAssertClose::test_none, test/test_testing.py::TestAssertClose::test_none_mismatch, test/test_testing.py::TestAssertClose::test_numpy, test/test_testing.py::TestAssertClose::test_only_atol, test/test_testing.py::TestAssertClose::test_only_rtol, test/test_testing.py::TestAssertClose::test_scalar, test/test_testing.py::TestAssertClose::test_unexpected_error_compare, test/test_testing.py::TestAssertClose::test_unexpected_error_originate, test/test_testing.py::TestAssertClose::test_unknown_layout, test/test_testing.py::TestAssertClose::test_unknown_type, test/test_testing.py::TestAssertCloseErrorMessage::test_abs_diff, test/test_testing.py::TestAssertCloseErrorMessage::test_abs_diff_scalar, test/test_testing.py::TestAssertCloseErrorMessage::test_atol, test/test_testing.py::TestAssertCloseErrorMessage::test_identifier_scalars, test/test_testing.py::TestAssertCloseErrorMessage::test_identifier_tensor_likes, test/test_testing.py::TestAssertCloseErrorMessage::test_mismatched_elements, test/test_testing.py::TestAssertCloseErrorMessage::test_msg_callable, test/test_testing.py::TestAssertCloseErrorMessage::test_msg_str, test/test_testing.py::TestAssertCloseErrorMessage::test_not_close, test/test_testing.py::TestAssertCloseErrorMessage::test_not_equal, test/test_testing.py::TestAssertCloseErrorMessage::test_rel_diff, test/test_testing.py::TestAssertCloseErrorMessage::test_rel_diff_scalar, test/test_testing.py::TestAssertCloseErrorMessage::test_rtol, test/test_testing.py::TestAssertCloseErrorMessage::test_small_float_dtype, test/test_testing.py::TestAssertCloseErrorMessage::test_zero_div_zero, test/test_testing.py::TestAssertCloseContainer::test_mapping_mismatching_keys, test/test_testing.py::TestAssertCloseContainer::test_mapping_mismatching_values_msg, test/test_testing.py::TestAssertCloseContainer::test_sequence_mismatching_len, test/test_testing.py::TestAssertCloseContainer::test_sequence_mismatching_values_msg, test/test_testing.py::TestAssertCloseSparseCOO::test_matching_coalesced, test/test_testing.py::TestAssertCloseSparseCOO::test_matching_uncoalesced, test/test_testing.py::TestAssertCloseSparseCOO::test_mismatching_indices_msg, test/test_testing.py::TestAssertCloseSparseCOO::test_mismatching_nnz, test/test_testing.py::TestAssertCloseSparseCOO::test_mismatching_sparse_dims, test/test_testing.py::TestAssertCloseSparseCOO::test_mismatching_values_msg, test/test_testing.py::TestAssertCloseSparseCSR::test_matching, test/test_testing.py::TestAssertCloseSparseCSR::test_mismatching_col_indices_msg, test/test_testing.py::TestAssertCloseSparseCSR::test_mismatching_crow_indices_msg, test/test_testing.py::TestAssertCloseSparseCSR::test_mismatching_values_msg, test/test_testing.py::TestAssertCloseSparseCSC::test_matching, test/test_testing.py::TestAssertCloseSparseCSC::test_mismatching_ccol_indices_msg, test/test_testing.py::TestAssertCloseSparseCSC::test_mismatching_row_indices_msg, test/test_testing.py::TestAssertCloseSparseCSC::test_mismatching_values_msg, test/test_testing.py::TestAssertCloseSparseBSR::test_matching, test/test_testing.py::TestAssertCloseSparseBSR::test_mismatching_col_indices_msg, test/test_testing.py::TestAssertCloseSparseBSR::test_mismatching_crow_indices_msg, test/test_testing.py::TestAssertCloseSparseBSR::test_mismatching_values_msg, test/test_testing.py::TestAssertCloseSparseBSC::test_matching, test/test_testing.py::TestAssertCloseSparseBSC::test_mismatching_ccol_indices_msg, test/test_testing.py::TestAssertCloseSparseBSC::test_mismatching_row_indices_msg, test/test_testing.py::TestAssertCloseSparseBSC::test_mismatching_values_msg, test/test_testing.py::TestAssertCloseQuantized::test_matching_per_channel, test/test_testing.py::TestAssertCloseQuantized::test_matching_per_tensor, test/test_testing.py::TestAssertCloseQuantized::test_mismatching_is_quantized, test/test_testing.py::TestAssertCloseQuantized::test_mismatching_qscheme, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_exclude_zero_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high0_value_types3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high1_value_types3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_ge_high_low_high2_value_types3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_boolean_integral2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_default_smoke_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_nan_low_high2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_outside_valid_range_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_low_high_smoke_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_memory_format_memory_format_and_shape4_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_memory_format_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape4_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape5_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_False_shape6_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape0_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape1_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape2_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape3_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape4_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape5_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_noncontiguous_noncontiguous_True_shape6_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_requires_grad_requires_grad_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape0_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape1_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape2_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape3_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape4_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape5_splat_shape_True_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_False_cpu_uint8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_bfloat16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_bool, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_complex128, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_complex32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_complex64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_float16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_float32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_float64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_int16, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_int32, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_int64, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_int8, test/test_testing.py::TestMakeTensorCPU::test_smoke_shape6_splat_shape_True_cpu_uint8, test/test_testing.py::TestTestParametrization::test_apply_param_specific_decorators, test/test_testing.py::TestTestParametrization::test_compose_param_specific_decorators, test/test_testing.py::TestTestParametrization::test_default_names, test/test_testing.py::TestTestParametrization::test_modules_decorator_misuse_error, test/test_testing.py::TestTestParametrization::test_multiple_handling_of_same_param_error, test/test_testing.py::TestTestParametrization::test_name_fn, test/test_testing.py::TestTestParametrization::test_ops_decorator_misuse_error, test/test_testing.py::TestTestParametrization::test_reparametrize, test/test_testing.py::TestTestParametrization::test_subtest_expected_failure_x_1, test/test_testing.py::TestTestParametrization::test_subtest_expected_failure_x_2, test/test_testing.py::TestTestParametrization::test_subtest_expected_failure_x_3, test/test_testing.py::TestTestParametrization::test_subtest_names, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_1_y_4, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_1_y_5, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_1_y_6, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_2_y_4, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_2_y_5, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_2_y_6, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_3_y_4, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_3_y_5, test/test_testing.py::TestTestParametrization::test_two_things_subtest_expected_failure_x_3_y_6, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_default_name_non_primitive_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_default_names_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_dtypes_composition_invalid_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_dtypes_composition_valid_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_empty_param_list_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_empty_param_names_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_modules_composition_names_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_modules_decorator_applies_module_and_param_specific_decorators_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_multiple_handling_of_same_param_error_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_name_fn_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_ops_composition_names_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_ops_decorator_applies_op_and_param_specific_decorators_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_param_specific_decoration_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_subtest_expected_failure_x_1_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_subtest_expected_failure_x_2_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_subtest_expected_failure_x_3_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_subtest_names_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_1_y_4_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_1_y_5_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_1_y_6_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_2_y_4_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_2_y_5_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_2_y_6_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_3_y_4_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_3_y_5_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_two_things_subtest_expected_failure_x_3_y_6_cpu, test/test_testing.py::TestTestParametrizationDeviceTypeCPU::test_unparametrized_names_cpu, test/test_testing.py::TestImports::test_circular_dependencies, test/test_testing.py::TestImports::test_lazy_imports_are_lazy, test/test_testing.py::TestImports::test_no_mutate_global_logging_on_import_path_functorch, test/test_testing.py::TestImports::test_no_mutate_global_logging_on_import_path_torch, test/test_testing.py::TestImports::test_no_warning_on_import, test/test_testing.py::TestImports::test_not_import_sympy, test/test_testing.py::TestImports::test_not_import_triton, test/test_testing.py::TestOpInfos::test_sample_input, test/test_testing.py::TestOpInfos::test_sample_input_metadata, test/test_testing.py::TestHardwareClassifications::test_filter_suite, test/test_testing.py::TestHardwareClassifications::test_filter_suite_uses_inherited_metadata, test/test_testing.py::TestHardwareClassifications::test_hw_classification_test_loader, test/test_testing.py::TestHardwareClassifications::test_hw_classification_test_loader_no_filter, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_T_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___radd___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rand___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rdiv___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rmod___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rmul___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___ror___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rpow___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rsub___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators___rxor___cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators__chunk_cat_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_add_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_amax_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_amin_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_aminmax_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_arange_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_as_strided_scatter_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_atan2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bernoulli_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bitwise_and_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bitwise_left_shift_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bitwise_or_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bitwise_right_shift_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bitwise_xor_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_bucketize_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_cat_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_cauchy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_clamp_max_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_clamp_min_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_complex_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_copysign_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_cov_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_diag_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_diag_embed_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_diagonal_copy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_diagonal_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_diff_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_div_floor_rounding_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_div_no_rounding_mode_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_div_trunc_rounding_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_dot_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_dsplit_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_dstack_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_empty_permuted_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_eq_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_exponential_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_eye_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_fft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_fft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_fftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_hfft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_hfft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_hfftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ifft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ifft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ifftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ihfft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ihfft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_ihfftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_irfft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_irfft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_irfftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_rfft2_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_rfft_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fft_rfftn_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fliplr_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_flipud_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_float_power_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_floor_divide_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fmax_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fmin_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_fmod_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_gather_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_gcd_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_ge_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_geometric_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_gradient_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_gt_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_heaviside_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_histogramdd_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_hsplit_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_hstack_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_hypot_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_igamma_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_igammac_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_index_add_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_index_select_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_isclose_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_item_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_jiterator_binary_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_jiterator_binary_return_by_ref_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_kthvalue_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_lcm_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_ldexp_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_le_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linalg_cross_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linalg_diagonal_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linalg_lstsq_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linalg_lstsq_grad_oriented_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linspace_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_linspace_tensor_overload_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_log_normal_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logaddexp_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logcumsumexp_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logical_and_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logical_or_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logical_xor_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logspace_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_logspace_tensor_overload_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_lt_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_masked_fill_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_masked_scatter_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_masked_select_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_max_binary_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_maximum_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_mean_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_median_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_min_binary_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_minimum_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_movedim_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_mul_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_multinomial_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_narrow_copy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_narrow_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_native_layer_norm_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_ne_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_neg_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nextafter_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_avg_pool1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_avg_pool2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_avg_pool3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_max_pool1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_max_pool2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_adaptive_max_pool3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_avg_pool1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_avg_pool2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_avg_pool3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_conv1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_conv2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_conv3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_embedding_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_gaussian_nll_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_gelu_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_group_norm_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_hardtanh_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_hinge_embedding_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_huber_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_l1_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_linear_cross_entropy_chunked_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_linear_cross_entropy_chunked_none_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_linear_cross_entropy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_margin_ranking_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_pool1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_pool2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_pool3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_unpool1d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_unpool2d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_max_unpool3d_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_multi_margin_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_multilabel_margin_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_poisson_nll_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_prelu_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_rms_norm_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_rrelu_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_soft_margin_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_softshrink_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_triplet_margin_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_nn_functional_triplet_margin_with_distance_loss_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_normal_in_place_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_ormqr_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_polar_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_pow_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_remainder_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_renorm_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_reshape_as_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_reshape_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_roll_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_rot90_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_rsub_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_scatter_add_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_scatter_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_bartlett_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_blackman_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_cosine_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_exponential_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_gaussian_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_general_cosine_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_general_hamming_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_hamming_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_hann_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_kaiser_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_signal_windows_nuttall_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_chebyshev_polynomial_t_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_chebyshev_polynomial_u_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_chebyshev_polynomial_v_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_chebyshev_polynomial_w_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_hermite_polynomial_h_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_hermite_polynomial_he_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_laguerre_polynomial_l_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_legendre_polynomial_p_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_shifted_chebyshev_polynomial_t_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_shifted_chebyshev_polynomial_u_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_shifted_chebyshev_polynomial_v_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_shifted_chebyshev_polynomial_w_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_xlog1py_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_special_zeta_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_sub_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_sum_to_size_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_t_copy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_t_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_take_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_trace_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_tril_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_triu_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_true_divide_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_unbind_copy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_unbind_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_uniform_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_vdot_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_view_as_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_view_copy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_view_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_vsplit_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_vstack_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_where_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_error_generators_xlogy_cpu, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___radd___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rand___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rdiv___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rmod___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rmul___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___ror___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rpow___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rsub___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators___rxor___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_abs_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_acos_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_acosh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_add_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_addcdiv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_addcmul_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_angle_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_asin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_asinh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_atan2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_atan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_atanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bfloat16_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_and_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_left_shift_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_not_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_or_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_right_shift_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bitwise_xor_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bool_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_broadcast_tensors_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_bucketize_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_byte_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_cat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_cdouble_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_ceil_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_cfloat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_chalf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_char_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_chunk_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_clamp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_clamp_max_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_clamp_min_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_clone_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_complex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_conj_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_conj_physical_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_contiguous_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_copysign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_cos_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_cosh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_deg2rad_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_diag_embed_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_diagonal_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_diagonal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_digamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_div_floor_rounding_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_div_no_rounding_mode_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_div_trunc_rounding_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_double_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_empty_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_eq_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_erf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_erfc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_erfinv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_exp2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_exp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_expm1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_fill_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_flatten_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_float_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_float_power_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_floor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_floor_divide_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_fmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_fmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_fmod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_frac_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_frexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_gcd_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_ge_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_gt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_half_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_heaviside_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_hypot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_i0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_igamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_igammac_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_imag_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_index_add_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_index_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_index_fill_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_index_select_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_int_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isclose_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isfinite_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isinf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isnan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isneginf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isposinf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_isreal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_jiterator_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_jiterator_binary_return_by_ref_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_jiterator_unary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_lcm_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_ldexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_le_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_lgamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_log10_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_log1p_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_log2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_log_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logaddexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logical_and_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logical_not_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logical_or_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logical_xor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_logsumexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_long_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_lt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_max_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_maximum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_min_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_minimum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_movedim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_mul_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_mvlgamma_mvlgamma_p_1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_mvlgamma_mvlgamma_p_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_mvlgamma_mvlgamma_p_5_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nan_to_num_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_narrow_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_narrow_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_native_group_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_ne_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_neg_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nextafter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_celu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_elu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_grid_sample_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_group_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_hardshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_hardsigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_hardtanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_hinge_embedding_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_interpolate_bicubic_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_interpolate_bilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_logsigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_margin_ranking_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_mish_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_multi_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_multilabel_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_prelu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_relu6_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_relu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_rrelu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_selu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_silu_complex_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_silu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_softplus_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_softshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_softsign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_tanhshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_threshold_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_nn_functional_upsample_bilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_permute_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_permute_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polar_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polygamma_polygamma_n_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polygamma_polygamma_n_1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polygamma_polygamma_n_2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polygamma_polygamma_n_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_polygamma_polygamma_n_4_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_positive_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_pow_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_rad2deg_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_real_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_reciprocal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_remainder_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_reshape_as_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_reshape_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_round_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_round_decimals_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_round_decimals_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_round_decimals_neg_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_rsqrt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_rsub_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sgn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_short_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_bartlett_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_blackman_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_cosine_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_exponential_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_gaussian_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_general_cosine_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_general_hamming_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_hamming_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_hann_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_kaiser_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signal_windows_nuttall_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_signbit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sinc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sinh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_airy_ai_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_bessel_j0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_bessel_j1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_bessel_y0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_bessel_y1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_chebyshev_polynomial_t_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_chebyshev_polynomial_u_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_chebyshev_polynomial_v_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_chebyshev_polynomial_w_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_entr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_erfcx_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_hermite_polynomial_h_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_hermite_polynomial_he_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_i0e_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_i1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_i1e_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_laguerre_polynomial_l_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_legendre_polynomial_p_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_log_ndtr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_modified_bessel_i0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_modified_bessel_i1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_modified_bessel_k0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_modified_bessel_k1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_ndtr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_ndtri_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_polygamma_special_polygamma_n_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_scaled_modified_bessel_k0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_scaled_modified_bessel_k1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_shifted_chebyshev_polynomial_t_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_shifted_chebyshev_polynomial_u_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_shifted_chebyshev_polynomial_v_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_shifted_chebyshev_polynomial_w_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_spherical_bessel_j0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_xlog1py_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_special_zeta_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sqrt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_square_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_sub_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_tan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_tanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_true_divide_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_trunc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_unsafe_chunk_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_view_as_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_view_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_where_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_reference_generators_xlogy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_H_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_T_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___getitem___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___radd___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rand___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rdiv___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rmatmul___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rmod___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rmul___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___ror___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rpow___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rsub___cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators___rxor___cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__batch_norm_with_update_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__chunk_cat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__native_batch_norm_legit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__segment_reduce_lengths_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__segment_reduce_offsets_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__softmax_backward_data_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__unsafe_masked_index_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__unsafe_masked_index_put_accumulate_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators__upsample_bilinear2d_aa_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_abs_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_acos_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_acosh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_add_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addbmm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addcdiv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addcmul_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addmm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addmm_decomposed_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addmv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_addr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_alias_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_all_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_allclose_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_amax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_amin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_aminmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_angle_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_any_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_arange_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_argmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_argmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_argsort_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_argwhere_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_as_strided_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_as_strided_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_as_strided_partial_views_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_as_strided_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_asin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_asinh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atan2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atleast_1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atleast_2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_atleast_3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_baddbmm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bernoulli_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bfloat16_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bincount_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_and_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_left_shift_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_not_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_or_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_right_shift_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bitwise_xor_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_block_diag_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bmm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bmm_triton_optimized_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bool_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_broadcast_shapes_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_broadcast_tensors_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_broadcast_to_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_bucketize_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_byte_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cartesian_prod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cauchy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cdist_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cdouble_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ceil_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cfloat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_chalf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_char_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cholesky_inverse_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cholesky_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_chunk_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_clamp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_clamp_max_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_clamp_min_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_clone_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_column_stack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_combinations_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_complex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_conj_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_conj_physical_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_constant_pad_nd_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_contiguous_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_copysign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_corrcoef_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cos_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cosh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_count_nonzero_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cov_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cross_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cummax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cummin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cumprod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cumsum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_cumulative_trapezoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_deg2rad_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diag_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diag_embed_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diagflat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diagonal_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diagonal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diagonal_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_diff_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_digamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_dist_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_div_floor_rounding_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_div_no_rounding_mode_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_div_trunc_rounding_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_dot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_double_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_dsplit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_dstack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_einsum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_empty_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_empty_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_empty_permuted_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_empty_strided_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_eq_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_equal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_erf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_erfc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_erfinv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_exp2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_exp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_expand_as_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_expand_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_expand_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_expm1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_exponential_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_eye_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_fft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_fft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_fftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_fftshift_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_hfft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_hfft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_hfftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ifft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ifft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ifftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ifftshift_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ihfft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ihfft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_ihfftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_irfft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_irfft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_irfftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_rfft2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_rfft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fft_rfftn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fill_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_flatten_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_flip_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fliplr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_flipud_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_float_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_float_power_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_floor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_floor_divide_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_fmod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_frac_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_frexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_full_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_full_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_gather_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_gcd_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ge_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_geometric_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_geqrf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_gradient_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_grid_sampler_2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_grid_sampler_3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_gt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_half_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_hash_tensor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_heaviside_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_histc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_histogram_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_histogramdd_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_hsplit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_hstack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_hypot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_i0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_igamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_igammac_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_imag_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_add_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_fill_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_put_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_reduce_amax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_reduce_amin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_reduce_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_reduce_prod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_index_select_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_inner_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_int_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isclose_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isfinite_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isinf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isnan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isneginf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isposinf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_isreal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_istft_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_item_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_jiterator_2inputs_2outputs_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_jiterator_4inputs_with_extra_args_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_jiterator_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_jiterator_binary_return_by_ref_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_jiterator_unary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_kron_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_kthvalue_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lcm_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ldexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_le_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lerp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lgamma_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_cholesky_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_cholesky_ex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_cond_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_cross_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_det_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_diagonal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_eig_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_eigh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_eigvals_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_eigvalsh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_householder_product_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_inv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_inv_ex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_ldl_factor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_ldl_factor_ex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_ldl_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lstsq_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lstsq_grad_oriented_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lu_factor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lu_factor_ex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_lu_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_matrix_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_matrix_power_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_matrix_rank_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_matrix_rank_hermitian_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_matrix_sqrth_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_multi_dot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_norm_subgradients_at_zero_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_pinv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_pinv_hermitian_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_pinv_singular_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_polar_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_qr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_slogdet_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_solve_ex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_solve_triangular_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_svd_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_svdvals_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_tensorinv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_tensorsolve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_vander_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_vecdot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linalg_vector_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linspace_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_linspace_tensor_overload_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log10_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log1p_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log_normal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log_softmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_log_softmax_with_dtype_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logaddexp2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logaddexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logcumsumexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logdet_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logical_and_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logical_not_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logical_or_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logical_xor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logspace_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logspace_tensor_overload_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_logsumexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_long_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lu_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_lu_unpack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mH_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mT_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_amax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_amin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_argmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_argmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_cumprod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_cumsum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_fill_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_log_softmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_logaddexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_logsumexp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_median_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_normalize_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_prod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_select_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_softmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_softmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_std_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_sum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_masked_var_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_matmul_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_matrix_exp_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_max_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_max_pool2d_with_indices_backward_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_max_reduction_no_dim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_max_reduction_with_dim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_maximum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_median_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_meshgrid_list_of_tensors_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_meshgrid_variadic_tensors_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_min_binary_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_min_reduction_no_dim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_min_reduction_with_dim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_minimum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mode_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_movedim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_msort_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mul_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_multinomial_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mv_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mvlgamma_mvlgamma_p_1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mvlgamma_mvlgamma_p_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_mvlgamma_mvlgamma_p_5_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nan_to_num_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nanmean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nanmedian_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nanquantile_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nansum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_narrow_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_narrow_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_native_batch_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_native_dropout_backward_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_native_group_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_native_layer_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ne_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_neg_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_new_empty_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_new_empty_strided_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_new_full_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_new_ones_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_new_zeros_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nextafter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_avg_pool1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_avg_pool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_avg_pool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_max_pool1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_max_pool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_adaptive_max_pool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_alpha_dropout_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_avg_pool1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_avg_pool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_avg_pool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_batch_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_bilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_binary_cross_entropy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_binary_cross_entropy_with_logits_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_celu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_channel_shuffle_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv_transpose1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv_transpose2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_conv_transpose3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_cosine_embedding_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_cosine_similarity_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_cross_entropy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_ctc_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_dropout2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_dropout3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_dropout_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_elu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_embedding_bag_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_embedding_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_feature_alpha_dropout_with_train_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_feature_alpha_dropout_without_train_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_fractional_max_pool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_fractional_max_pool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_gaussian_nll_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_gelu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_glu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_grid_sample_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_group_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_hardshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_hardsigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_hardswish_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_hardtanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_hinge_embedding_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_huber_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_instance_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_area_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_bicubic_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_bilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_linear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_nearest-exact_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_nearest_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_interpolate_trilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_kl_div_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_l1_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_layer_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_leaky_relu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_linear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_linear_cross_entropy_chunked_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_linear_cross_entropy_chunked_none_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_linear_cross_entropy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_local_response_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_logsigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_margin_ranking_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_pool1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_pool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_pool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool1d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool1d_grad_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool2d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool2d_grad_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool3d_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_max_unpool3d_grad_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_mish_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_mse_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_multi_head_attention_forward_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_multi_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_multilabel_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_multilabel_soft_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_nll_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_normalize_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_one_hot_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pad_circular_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pad_constant_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pad_reflect_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pad_replicate_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pad_replicate_negative_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pairwise_distance_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pdist_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pixel_shuffle_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_pixel_unshuffle_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_poisson_nll_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_prelu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_relu6_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_relu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_rms_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_rrelu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_scaled_dot_product_attention_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_selu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_silu_complex_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_silu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_smooth_l1_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_soft_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_softmin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_softmin_with_dtype_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_softplus_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_softshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_softsign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_tanhshrink_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_threshold_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_triplet_margin_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_triplet_margin_with_distance_loss_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_unfold_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_upsample_bilinear_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nn_functional_upsample_nearest_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nonzero_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_nonzero_static_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_norm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_norm_fro_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_norm_inf_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_norm_nuc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_normal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_normal_in_place_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_normal_number_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ones_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ones_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ormqr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_outer_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_pca_lowrank_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_permute_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_permute_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_pinverse_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polar_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polygamma_polygamma_n_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polygamma_polygamma_n_1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polygamma_polygamma_n_2_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polygamma_polygamma_n_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_polygamma_polygamma_n_4_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_positive_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_pow_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_prod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_put_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_quantile_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_rad2deg_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_rand_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_randint_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_randint_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_randn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_randn_like_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_ravel_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_real_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_reciprocal_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_remainder_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_renorm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_repeat_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_repeat_interleave_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_reshape_as_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_reshape_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_resize__cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_resize_as__cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_resolve_conj_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_resolve_neg_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_roll_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_rot90_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_round_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_round_decimals_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_round_decimals_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_round_decimals_neg_3_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_rsqrt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_rsub_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scalar_tensor_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_add_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_reduce_amax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_reduce_amin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_reduce_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_reduce_prod_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_scatter_reduce_sum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_searchsorted_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_select_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_select_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sgn_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_short_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sigmoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sign_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_bartlett_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_blackman_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_cosine_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_exponential_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_gaussian_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_general_cosine_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_general_hamming_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_hamming_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_hann_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_kaiser_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signal_windows_nuttall_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_signbit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sin_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sinc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sinh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_slice_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_slice_scatter_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_softmax_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_softmax_with_dtype_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sort_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sparse_mm_reduce_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sparse_sampled_addmm_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_airy_ai_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_bessel_j0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_bessel_j1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_bessel_y0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_bessel_y1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_chebyshev_polynomial_t_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_chebyshev_polynomial_u_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_chebyshev_polynomial_v_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_chebyshev_polynomial_w_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_entr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_erfcx_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_hermite_polynomial_h_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_hermite_polynomial_he_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_i0e_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_i1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_i1e_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_laguerre_polynomial_l_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_legendre_polynomial_p_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_log_ndtr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_modified_bessel_i0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_modified_bessel_i1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_modified_bessel_k0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_modified_bessel_k1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_ndtr_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_ndtri_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_polygamma_special_polygamma_n_0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_scaled_modified_bessel_k0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_scaled_modified_bessel_k1_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_shifted_chebyshev_polynomial_t_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_shifted_chebyshev_polynomial_u_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_shifted_chebyshev_polynomial_v_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_shifted_chebyshev_polynomial_w_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_spherical_bessel_j0_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_xlog1py_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_special_zeta_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_split_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_split_list_args_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_split_with_sizes_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_split_with_sizes_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sqrt_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_square_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_squeeze_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_squeeze_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_squeeze_multiple_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_stack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_std_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_std_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_std_mean_unbiased_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_std_unbiased_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_stft_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sub_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sum_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_sum_to_size_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_svd_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_svd_lowrank_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_t_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_t_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_take_along_dim_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_take_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tan_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tanh_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tensor_split_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tensordot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tile_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_to_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_to_sparse_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_topk_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_torch__scaled_mm_cpu_float8_e4m3fn, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_torch__scaled_mm_v2_cpu_float8_e4m3fn, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_torch_ops_aten__safe_softmax_default_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_torch_ops_aten__scaled_dot_product_flash_attention_for_cpu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_trace_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_transpose_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_transpose_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_trapezoid_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_trapz_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_triangular_solve_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tril_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_tril_indices_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_triu_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_triu_indices_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_true_divide_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_trunc_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unbind_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unbind_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unflatten_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unfold_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unfold_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_uniform_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unique_consecutive_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unique_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unravel_index_cpu_int64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unsafe_chunk_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unsafe_split_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unsqueeze_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_unsqueeze_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_var_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_var_mean_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_var_mean_unbiased_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_var_unbiased_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_vdot_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_view_as_complex_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_view_as_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_view_as_real_cpu_complex64, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_view_copy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_view_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_vsplit_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_vstack_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_where_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_xlogy_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_zero__cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_zeros_cpu_float32, test/test_testing.py::TestOpInfoSampleFunctionsCPU::test_opinfo_sample_generators_zeros_like_cpu_float32
2026-07-31T06:23:48.5698990Z 
2026-07-31T06:23:48.5699230Z Finished test_testing 1/1 ... [2026-07-31 06:23:48.448895][413268.666089333], took 0.48min
2026-07-31T06:23:48.7364250Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_testing/test_testing-c05c22c82e510709.xml
2026-07-31T06:28:04.5274680Z 
2026-07-31T06:28:04.5275410Z test_transformers 1/2 was successful, full logs can be found in artifacts with path test/test-reports/test_transformers_1.2_937869aa3f09ca5d_.log
2026-07-31T06:28:04.6465410Z Running 1772 items in this shard: test/test_transformers.py::TestTransformersCPU::test_bias_is_none_cpu, test/test_transformers.py::TestTransformersCPU::test_decoder_only_layer_cpu, test/test_transformers.py::TestTransformersCPU::test_encoder_padding_and_src_mask_bool_cpu, test/test_transformers.py::TestTransformersCPU::test_is_causal_gpu_cpu, test/test_transformers.py::TestTransformersCPU::test_kpm_mask_trailing_column_with_nested_tensor_cpu, test/test_transformers.py::TestTransformersCPU::test_mask_check_fastpath_cpu, test/test_transformers.py::TestTransformersCPU::test_mha_native_args_nb_heads_1_bias_False_cpu, test/test_transformers.py::TestTransformersCPU::test_mha_native_args_nb_heads_8_bias_True_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim2_key_padding_mask_dim1_bool_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim2_key_padding_mask_dim_2_float32_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim_2_key_padding_mask_dim_2_bool_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim_2_key_padding_mask_dim_2_float32_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim_3_key_padding_mask_dim1_bool_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim_3_key_padding_mask_dim1_float32_cpu, test/test_transformers.py::TestTransformersCPU::test_multiheadattention_fastpath_attn_mask_attn_mask_dim_3_key_padding_mask_dim_2_bool_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_2D_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_2D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_2D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_2D_causal_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_3D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_3D_causal_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_no_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_3D_input_dim_no_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_2D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_2D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_4D_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_4D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_4D_causal_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_4D_causal_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_4D_causal_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_no_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_1_4D_input_dim_no_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_2D_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_2D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_2D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_2D_causal_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_3D_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_3D_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_3D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_3D_causal_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_3D_causal_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_no_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_3D_input_dim_no_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_2D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_4D_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_4D_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_4D_causal_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_4D_causal_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_4D_causal_attn_mask_dropout_p_0_5_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_no_attn_mask_dropout_p_0_0_cpu, test/test_transformers.py::TestTransformersCPU::test_scaled_dot_product_attention_batch_size_5_4D_input_dim_no_attn_mask_dropout_p_0_2_cpu, test/test_transformers.py::TestTransformersCPU::test_script_mha_in_proj_weight_none_cpu, test/test_transformers.py::TestTransformersCPU::test_self_attn_TxT_attn_mask_cpu, test/test_transformers.py::TestTransformersCPU::test_train_with_pad_and_catch_error_cpu, test/test_transformers.py::TestTransformersCPU::test_transformer_bias_is_none_cpu, test/test_transformers.py::TestTransformersCPU::test_transformer_encoder_layer_fwd_fake_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_batch_first_False_training_False_enable_nested_tensor_False_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_batch_first_False_training_False_enable_nested_tensor_True_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_batch_first_False_training_True_enable_nested_tensor_False_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_batch_first_False_training_True_enable_nested_tensor_True_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_batch_first_True_training_True_enable_nested_tensor_True_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_fastpath_use_torchscript_False_enable_nested_tensor_False_use_autocast_False_d_model_12_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_fastpath_use_torchscript_False_enable_nested_tensor_False_use_autocast_False_d_model_256_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_fastpath_use_torchscript_False_enable_nested_tensor_False_use_autocast_True_d_model_12_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_fastpath_use_torchscript_False_enable_nested_tensor_False_use_autocast_True_d_model_256_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_fastpath_use_torchscript_False_enable_nested_tensor_True_use_autocast_False_d_model_256_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoder_square_input_with_no_grad_False_training_True_enable_nested_tensor_False_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoderlayer_src_mask_nhead_4_cpu, test/test_transformers.py::TestTransformersCPU::test_transformerencoderlayer_subclass_model_cpu, test/test_transformers.py::TestTransformersCPU::test_with_nested_tensor_input_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_cudnn_attention_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_default_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_error_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_flash_attention_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_math_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_attn_mask_and_is_causal_errors_before_dispatch_overrideable_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_flash_atteention_large_bf16_nan_values_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_flash_attention_fail_with_non_square_causal_attention_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_flash_backward_failure_sm86plus_head_dim_193_dropout_p_0_0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_flash_backward_failure_sm86plus_head_dim_256_dropout_p_0_2_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_flash_fail_fp32_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_fused_kernels_nested_broadcasting_error_cases_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_fused_kernels_nested_broadcasting_requires_grad_failure_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_fused_kernels_seq_len_0_inputs_fused_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_fused_inputs_attn_mask_present_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_fused_inputs_broadcast_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_fused_inputs_dim_3_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_fused_inputs_invalid_dtype_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_1_dimensional_inputs_kernel1_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_1_dimensional_inputs_kernel2_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_different_datatypes_kernel1_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_different_datatypes_kernel2_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_different_devices_kernel1_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_inputs_different_devices_kernel2_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_invalid_last_dim_stride_kernel0_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_mem_eff_attention_fail_with_batch_size_geq_65536_error_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_mem_efficient_fail_bfloat16_less_than_sm80_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_nested_fails_on_padding_head_dim_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_sdpa_empty_unbacked_no_dde_cpu, test/test_transformers.py::TestSDPAFailureModesCPU::test_unaligned_tensors_cpu, test/test_transformers.py::TestSDPAFailureModesMPS::test_attn_mask_and_is_causal_errors_before_dispatch_default_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_attn_mask_and_is_causal_errors_before_dispatch_efficient_attention_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_attn_mask_and_is_causal_errors_before_dispatch_error_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_attn_mask_and_is_causal_errors_before_dispatch_flash_attention_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_attn_mask_and_is_causal_errors_before_dispatch_math_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_atteention_large_bf16_nan_values_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_attention_fail_with_non_square_causal_attention_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_autocast_fp32_bfloat16_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_autocast_fp32_float16_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_backward_failure_sm86plus_head_dim_193_dropout_p_0_0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_backward_failure_sm86plus_head_dim_193_dropout_p_0_2_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_backward_failure_sm86plus_head_dim_256_dropout_p_0_0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_flash_fail_fp32_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_fused_kernels_nested_broadcasting_error_cases_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_fused_kernels_nested_broadcasting_requires_grad_failure_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_fused_inputs_broadcast_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_fused_inputs_head_dim_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_fused_inputs_invalid_dtype_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_inputs_1_dimensional_inputs_kernel1_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_inputs_different_datatypes_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_inputs_different_datatypes_kernel1_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_inputs_different_devices_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_inputs_different_devices_kernel2_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_invalid_last_dim_stride_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_mask_invalid_last_dim_stride_kernel0_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_mem_eff_attention_backward_requires_bias_when_bias_grad_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_mem_eff_attention_fail_with_batch_size_geq_65536_error_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_mem_eff_attention_large_seq_len_attn_mask_index_overflow_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_mem_efficient_fail_bfloat16_less_than_sm80_mps, test/test_transformers.py::TestSDPAFailureModesMPS::test_zero_sequence_lengths_mps, test/test_transformers.py::TestSDPACPU::test_scaled_dot_product_attention_fp16_overflow_cpu, test/test_transformers.py::TestSDPACPU::test_sdpa_output_shape_uses_value_head_dim_cpu, test/test_transformers.py::TestSDPACPU::test_sdpa_zero_output_q_shape4_k_shape4_v_shape4_cpu, test/test_transformers.py::TestSDPACPU::test_sdpa_zero_output_q_shape5_k_shape5_v_shape5_cpu, test/test_transformers.py::TestSDPACPU::test_sdpa_zero_qk_head_dim_matches_eager_attention_value_dim_1_scale_1_0_cpu, test/test_transformers.py::TestSDPACPU::test_sdpa_zero_qk_head_dim_matches_eager_attention_value_dim_8_scale_1_0_cpu, test/test_transformers.py::TestSDPAMPS::test_sdp_math_gradcheck_contiguous_inputs_False_mps, test/test_transformers.py::TestSDPAMPS::test_sdpa_export_unbacked_attn_mask_mps, test/test_transformers.py::TestSDPAMPS::test_sdpa_zero_output_q_shape0_k_shape0_v_shape0_mps, test/test_transformers.py::TestSDPAMPS::test_sdpa_zero_output_q_shape1_k_shape1_v_shape1_mps, test/test_transformers.py::TestSDPACpuOnlyCPU::test_cpu_flash_attn_nan_propagation_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_128_head_dim_16_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_128_head_dim_16_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_128_head_dim_32_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_128_head_dim_32_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_32_head_dim_32_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_32_head_dim_32_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_64_head_dim_16_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_64_head_dim_16_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend0_seq_len_64_head_dim_32_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend1_seq_len_128_head_dim_16_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fully_masked_out_rows_backend1_seq_len_32_head_dim_16_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_dense_dropout_0_0_float16_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_dense_dropout_0_0_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_dense_dropout_0_0_float64_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_dense_dropout_0_7_float64_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_nested_dropout_0_0_bfloat16_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_nested_dropout_0_7_bfloat16_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_nested_dropout_0_7_float32_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_fused_sdp_choice_cpu_type_nested_dropout_0_7_float64_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_mqa_singleton_head_broadcast_cpu, test/test_transformers.py::TestSDPACpuOnlyCPU::test_non_masked_rows_nan_props_float32_fill_val_inf_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_attention_math_with_negative_scale_kernel0_cpu, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_bfloat16_n_heads0_train_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_bfloat16_n_heads1_train_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float16_n_heads0_train_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float16_n_heads0_train_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float16_n_heads1_train_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float16_n_heads1_train_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float16_n_heads2_train_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float32_n_heads0_train_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float32_n_heads2_train_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float32_n_heads2_train_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float32_n_heads3_train_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_gqa_vs_math_cpu_fused_kernel0_float64_n_heads1_train_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_bfloat16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_bfloat16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float16_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float16, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float32_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float32, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_12_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_1030_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_11_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_17_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_1_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_False_train_True_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_2_bool_mask_True_train_True_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_False_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_False_casual_True_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_False_cpu_float64, test/test_transformers.py::TestSDPACpuOnlyCPU::test_scaled_dot_product_fused_attention_mask_vs_math_cpu_fused_kernel0_float64_batch_size_2_q_seq_len_514_kv_seq_len_514_n_head_3_head_dim_8_mask_dim_4_bool_mask_True_train_True_casual_False_set_attn_mask_True_cpu_float64, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_1_shape0_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_1_shape1_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_1_shape2_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_2_shape1_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_2_shape2_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_causal_variant_2_shape3_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_compile_causal_variant_1_shape1_cpu, test/test_transformers.py::TestAttnBiasCPU::test_causal_variants_compile_causal_variant_2_shape0_cpu, test/test_transformers.py::TestAttnBiasCPU::test_is_causal_and_mask_fails_cpu, test/test_transformers.py::TestAttnBiasCPU::test_is_causal_equals_upper_left_shape3_cpu
2026-07-31T06:28:04.7632400Z 
2026-07-31T06:28:04.7632640Z Finished test_transformers 1/2 ... [2026-07-31 06:28:04.530003][413524.750116333], took 4.60min
2026-07-31T06:28:05.0163850Z Running test batch 'tests to run' cost 5751.82 seconds
2026-07-31T06:28:05.0181310Z Emitting td_test_failure_stats_v2
#=MATCH=# 2026-07-31T06:28:05.2272960Z ‹nn/test_pruning› 1/1 failed! Received signal: ‹SIGBUS›
2026-07-31T06:28:05.2279310Z Parsing testcases for test report: /Users/ec2-user/runner/_work/pytorch/pytorch/test/test-reports/python-pytest/test_transformers/test_transformers-46b48ae40023141c.xml
2026-07-31T06:28:05.2280500Z Writing 1 documents to S3 ossci-raw-job-status/ossci_uploaded_metrics/td_test_failure_stats_v2_1785479285_fce0d7548ca811f1b789fa16359054fc
2026-07-31T06:28:05.2281590Z Done! Finish writing document to S3 ossci-raw-job-status/ossci_uploaded_metrics/td_test_failure_stats_v2_1785479285_fce0d7548ca811f1b789fa16359054fc 
2026-07-31T06:28:05.8099260Z ##[error]Process completed with exit code 1.
2026-07-31T06:28:05.8146700Z ##[group]Run cat test/**/*_toprint.log || true
2026-07-31T06:28:05.8146960Z [36;1mcat test/**/*_toprint.log || true[0m
2026-07-31T06:28:05.8898110Z shell: /bin/bash --noprofile --norc -e -o pipefail {0}
2026-07-31T06:28:05.8898350Z env:
2026-07-31T06:28:05.8898490Z   GIT_DEFAULT_BRANCH: main
2026-07-31T06:28:05.8898780Z   BUILD_ENVIRONMENT: macos-py3-arm64
2026-07-31T06:28:05.8898970Z   TEST_CONFIG: default
2026-07-31T06:28:05.8899120Z   SHARD_NUMBER: 1
2026-07-31T06:28:05.8899380Z   NUM_TEST_SHARDS: 3
2026-07-31T06:28:05.8899520Z   PR_BODY: 
2026-07-31T06:28:05.8899650Z   REINSTALL_BREW_MINICONDA: 1
2026-07-31T06:28:05.8899920Z   VENV_PATH: /Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466
2026-07-31T06:28:05.8900250Z   UV_PYTHON_INSTALL_DIR: /Users/ec2-user/.local/share/uv/python
2026-07-31T06:28:05.8900500Z   UV_PYTHON: 3.12
2026-07-31T06:28:05.8900640Z ##[endgroup]
2026-07-31T06:28:05.9470100Z cat: test/**/*_toprint.log: No such file or directory
2026-07-31T06:28:05.9502850Z ##[group]Run kill "$MONITOR_SCRIPT_PID"
2026-07-31T06:28:05.9503120Z [36;1mkill "$MONITOR_SCRIPT_PID"[0m
2026-07-31T06:28:05.9515390Z shell: /bin/bash -e -l {0}
2026-07-31T06:28:05.9515570Z env:
2026-07-31T06:28:05.9515710Z   GIT_DEFAULT_BRANCH: main
2026-07-31T06:28:05.9515930Z   BUILD_ENVIRONMENT: macos-py3-arm64
2026-07-31T06:28:05.9516180Z   TEST_CONFIG: default
2026-07-31T06:28:05.9516340Z   SHARD_NUMBER: 1
2026-07-31T06:28:05.9516510Z   NUM_TEST_SHARDS: 3
2026-07-31T06:28:05.9516700Z   PR_BODY: 
2026-07-31T06:28:05.9516840Z   REINSTALL_BREW_MINICONDA: 1
2026-07-31T06:28:05.9517110Z   VENV_PATH: /Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466
2026-07-31T06:28:05.9517460Z   UV_PYTHON_INSTALL_DIR: /Users/ec2-user/.local/share/uv/python
2026-07-31T06:28:05.9517730Z   UV_PYTHON: 3.12
2026-07-31T06:28:05.9517890Z   MONITOR_SCRIPT_PID: 82616
2026-07-31T06:28:05.9518070Z ##[endgroup]
2026-07-31T06:28:06.0043920Z Prepare all required actions
2026-07-31T06:28:06.0044360Z Getting action download info
2026-07-31T06:28:06.1125290Z Download action repository 'seemethere/upload-artifact-s3@v5' (SHA:baba72d0712b404f646cebe0730933554ebce96a)
2026-07-31T06:28:06.2477190Z Download action repository 'actions/upload-artifact@v4' (SHA:ea165f8d65b6e75b540449e92b4886f43607fa02)
2026-07-31T06:28:06.4154600Z Getting action download info
2026-07-31T06:28:06.5449640Z ##[group]Run ./.github/actions/upload-test-artifacts
2026-07-31T06:28:06.5449870Z with:
2026-07-31T06:28:06.5449990Z   use-gha: true
2026-07-31T06:28:06.5450200Z   file-suffix: test-default-1-3-macos-m1-stable_91075863282
2026-07-31T06:28:06.5450520Z   s3-bucket: gha-artifacts
2026-07-31T06:28:06.5450690Z   skip-s3: false
2026-07-31T06:28:06.5450830Z env:
2026-07-31T06:28:06.5450960Z   GIT_DEFAULT_BRANCH: main
2026-07-31T06:28:06.5451150Z   BUILD_ENVIRONMENT: macos-py3-arm64
2026-07-31T06:28:06.5451340Z   TEST_CONFIG: default
2026-07-31T06:28:06.5451500Z   SHARD_NUMBER: 1
2026-07-31T06:28:06.5451640Z   NUM_TEST_SHARDS: 3
2026-07-31T06:28:06.5451790Z   PR_BODY: 
2026-07-31T06:28:06.5451930Z   REINSTALL_BREW_MINICONDA: 1
2026-07-31T06:28:06.5452180Z   VENV_PATH: /Users/ec2-user/runner/_work/_temp/venv-3.12-1785473466
2026-07-31T06:28:06.5452500Z   UV_PYTHON_INSTALL_DIR: /Users/ec2-user/.local/share/uv/python
2026-07-31T06:28:06.5453000Z   UV_PYTHON: 3.12
2026-07-31T06:28:06.5453140Z ##[endgroup]
2026-07-31T06:28:06.5466420Z ##[start-action display=Setup uv;id=__self_3.__pytorch_test-infra]
