viable/strict/1789252151: [inductor] Gate CUDA TMA tests on CUDA devices (#196636)
- PyTorch: 850 events in the last 90 days
- PyTorch: 839th Release in the last 90 days
- Previous: earlier the same day · viable/strict/1789237655: Upgrade Nvidia's Windows CRCR Repo to L2 (#196602)
What happened
has_triton_tma_device() reports tensor-descriptor support when any installed Triton backend supports it, including CPU and XPU. A ROCm build that also bundles the Triton CPU backend can therefore return true even though its AMD GPU cannot run CUDA TMA templates. Add a CUDA-specific predicate requiring a non-HIP CUDA device with compute capability 9.0 or newer, and use it for the CUDA-only TMA tests. Keep the existin…
Summary assembled by rule from the sources below