[Inductor XPU GEMM] Step 5/N: Refactor CUDACombinedScheduling and CUDACppScheduling. by etaf · Pull Request #160688 · pytorch/pytorch

etaf · 2025-08-14T22:25:38Z

Stack from ghstack (oldest at bottom):

Following the design of #160175, This PR renamed CUDACppScheduling to CUTLASSScheduling so that they can be reused for XPU.

cc @jeffdaily @sunway513 @jithunnair-amd @pruthvistony @ROCmSupport @jataylo @hongxiayang @naromero77amd @pragupta @jerrymannil @xinyazhang @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @kadeng @muchulee8 @amjames @chauhang @aakhundov @coconutruben

…DACppScheduling. [ghstack-poisoned]

pytorch-bot · 2025-08-14T22:25:41Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/160688

📄 Preview Python docs built from this PR
📄 Preview C++ docs built from this PR
❓ Need help or want to give feedback on the CI? Visit the bot commands wiki

Note: Links to docs will display an error until the docs builds have been completed.

✅ You can merge normally! (9 Unrelated Failures)

As of commit 52c90e0 with merge base a2352cc ():

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

inductor / unit-test / inductor-test / test (inductor_distributed, 1, 1, linux.g5.12xlarge.nvidia.gpu) (gh) (disabled by #153223)
test/distributed/tensor/parallel/test_micro_pipeline_tp.py::MicroPipelineTPTest::test_dtensor_seq_par_shard_dim_1
trunk / linux-jammy-cuda12.8-py3.10-gcc11 / test (distributed, 2, 3, linux.g4dn.12xlarge.nvidia.gpu) (gh) (disabled by #153223)
test/distributed/tensor/parallel/test_micro_pipeline_tp.py::MicroPipelineTPTest::test_dtensor_seq_par_shard_dim_1
trunk / linux-jammy-cuda13.0-py3.10-gcc11 / test (distributed, 2, 3, linux.g4dn.12xlarge.nvidia.gpu) (gh) (disabled by #153223)
test/distributed/tensor/parallel/test_micro_pipeline_tp.py::MicroPipelineTPTest::test_dtensor_seq_par_shard_dim_1
trunk / linux-jammy-rocm-py3.10 / test (distributed, 2, 3, linux.rocm.gpu.gfx950.4) (gh) (disabled by #153223)
test/distributed/tensor/parallel/test_micro_pipeline_tp.py::MicroPipelineTPTest::test_dtensor_seq_par_shard_dim_1

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

inductor / inductor-cpu-test / test (cpu_inductor_torchbench, 2, 2, linux.2xlarge.amx) (gh) (trunk failure)
pytorch_CycleGAN_and_pix2pix
inductor / inductor-test / test (inductor_timm, 1, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
Process completed with exit code 1.
inductor / inductor-test / test (inductor_torchbench, 2, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
pytorch_CycleGAN_and_pix2pix
inductor / inductor-test-cuda13 / test (inductor_timm, 1, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
Process completed with exit code 1.
inductor / inductor-test-cuda13 / test (inductor_torchbench, 2, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
pytorch_CycleGAN_and_pix2pix

This comment was automatically generated by Dr. CI and updates every 15 minutes.

…DACppScheduling. ghstack-source-id: 425fbc2 Pull Request resolved: #160688

…ling and CUDACppScheduling." cc jeffdaily sunway513 jithunnair-amd pruthvistony ROCmSupport dllehr-amd jataylo hongxiayang naromero77amd voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov coconutruben [ghstack-poisoned]

…DACppScheduling. ghstack-source-id: 5a58c75 Pull Request resolved: #160688

…ing and CUDACppScheduling." cc jeffdaily sunway513 jithunnair-amd pruthvistony ROCmSupport dllehr-amd jataylo hongxiayang naromero77amd voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov coconutruben [ghstack-poisoned]

…ing and CUDACppScheduling." [ghstack-poisoned]