ciflow/trunk/201190: ATen: Support output-shaped FP8 residual bias on ROCm (#201190)
- PyTorch 近 90 天出现 2487 次
- PyTorch 近 90 天第 2454 次发版
- 上一次:同一天稍早 · ciflow/torchtitan/201289: [UPDATE] Update
发生了什么
Summary: Support a BF16 output-shaped residual through the v1 torch._scaled_mm bias argument on ROCm with rowwise input scales. Add the residual in the GEMM epilogue before BF16 rounding. Detect matrix residuals by their two-dimensional output shape, including single-row outputs; element count alone must not route [1, N] residuals as vector bias. Preserve vector-bias compatibility and CUDA matrix-bias rejection. Rej…
摘要按规则整理自下方来源原文