viable/strict/1788216615: [inductor] Enable BF16 index_add lowering on SM90+ and ROCm (#195192)
- PyTorch: 337 events in the last 90 days
- PyTorch: 334th Release in the last 90 days
- Previous: earlier the same day · viable/strict/1788213019
What happened
The Inductor index_add decomposition retained a stale OSS-only BF16 fallback after Triton added BF16 atomic_add support. This enables the decomposition on ROCm and on NVIDIA SM90+, allowing index_add to participate in fusion instead of becoming an ATen fallback kernel. Triton support was added in triton-lang/triton#6519 and was tested upstream on MI300 as well as NVIDIA GPUs. NVIDIA remains gated to SM90+ here becau…
Summary assembled by rule from the sources below