Crash on CPU: no diagnostic output or terminate called after throwing an instance of 'std::length_error'

XLA compilation (jit_compile=True) aborts with a fatal CHECK when compiling tf.where on the result of diagflat(tf.unique(...))

[Regression] `CollectivePipeliner` GPU pass present in JAX 0.4.38 is missing from JAX 0.10.1 — pipelining flags accepted but produce no pass stages; class symbols absent from binaries

Coverage-instrumented build: CPU JIT fails (`__profc_*` symbols not found); CUDA works

[GPU] Heap corruption during autotune-fusion-emitters on log-sum-exp with is_finite/select guard

[XLA] InternalError: mixed floating-point precision in TanhGrad during XLA compilation — f32 multiply sees mismatched types despite no explicit mixed precision

[XLA:CPU] Possible perf regression in `Worker::Parallelize`

Anyone working on RISC-V AI accelerators? Check TSU

Open RISC-V NPU architecture — worth a look for hardware folks

TSU Protocol: 16 custom AI instructions on RV64