← Back to events
ActiveAIRelease

ciflow/xpu/194864: [inductor] Use Inline ASM HOP in MXFP8 nested reduction test

Photo: PyTorch Releases

What happened

The MXFP8 nested-reduction test directly called the private cvt_e8m0_rceil prim, whose lowering only supports NVIDIA SM100+. This made the test fail on XPU and expanded the proposed fix into an unnecessary cross-device lowering. Use Inline ASM HOP on CUDA and ordinary tensor bit operations on XPU. This keeps the direct prim unchanged while exercising the same fused nested-reduction kernel on both backends. Test Plan…

Summary assembled by rule from the sources below

Why it's spreading

Sources