warpgroup_mma_wait does not properly synchronize across warpgroups

assertion failure at mlir::triton::ColumnAction::apply in triton/lib/Tools/LinearLayout.cpp

[BUG] sm_103 (B300): `tl.dot` chunked-recurrence kernel is non-deterministic with `num_warps∈{4,8}, num_stages∈{2,3}` — reproduces on Triton 3.7.0, i.e. NOT fixed by #9615 / #9871's fix

[v.3.7.1] Release Tracker

Probabilistic illegal memory access from a kernel with multiple tl.dot on H100 (sm_90)

`make_llir` ~8-minute O(n²) stall after LLVM bump #9746 (BuiltinFuncToLLVM / simplifyRegions) on AMD backend

Inquiry: How does Triton handle precision differences caused by summation order in tl.sum?

AMD: `tritonamdgpu-canonicalize-pointers` asserts on `tl.where` between two base pointers (gfx1150)

TritonGPURemoveLayoutConversions dominance failure compiling vLLM fused_moe_kernel on sm87

Triton v3.7.0 - Folder examples/plugins not included into the release