ciflow/b200/194364: Inductor: fix NVGEMM EFC reduction fallback
- PyTorch 近 90 天出现 1016 次
- PyTorch 近 90 天第 1005 次发版
- 上一次:同一天稍早 · viable/strict/1789514701: [Inductor] Eliminate no-op self slice_scatter after split (#195608)
发生了什么
Cutlass Operators 0.2 moved the shared EFC module, so import it independently from the optional dense EFC class. Preserve the identity finalizer needed by generated reductions. Direct EFC supports one generated reduction. Defer only selected composite reduction plans, which otherwise produce invalid results, and validate the regular NVGEMM fallback. Update tests to assert supported behavior rather than unsupported o…
摘要按规则整理自下方来源原文