diff --git a/.github/workflows/release-whl-deepgemm.yml b/.github/workflows/release-whl-deepgemm.yml index 3d59ffc00..40f86ec67 100644 --- a/.github/workflows/release-whl-deepgemm.yml +++ b/.github/workflows/release-whl-deepgemm.yml @@ -79,57 +79,8 @@ jobs: name: deepgemm-wheel-cuda${{ matrix.cuda-version }}-${{ matrix.arch }} path: DeepGEMM/dist/*.whl - test-cu129: - needs: build-cu129-matrix - strategy: - fail-fast: false - matrix: - include: - - arch_label: sm90 - runner: 8-gpu-h200 - wheel_arch: x86_64 - - arch_label: sm100 - runner: 8-gpu-b200 - wheel_arch: x86_64 - runs-on: ${{ matrix.runner }} - timeout-minutes: 120 - steps: - - uses: actions/checkout@v4 - - - name: Checkout DeepGEMM - uses: actions/checkout@v4 - with: - repository: sgl-project/DeepGEMM - ref: ${{ inputs.branch || 'dev' }} - path: DeepGEMM - submodules: recursive - - - name: Download wheel - uses: actions/download-artifact@v4 - with: - path: dist/ - merge-multiple: true - pattern: deepgemm-wheel-cuda12.9-${{ matrix.wheel_arch }} - - - name: Install wheel and deps - env: - CU_TAG: cu129 - run: | - python3 -m pip install --upgrade pip - # deep_gemm imports torch before loading _C.so, so torch must preload the - # libcudart the cu129 wheel links. Pin the CUDA-matched torch (see sgl-deep-gemm.Dockerfile). - python3 -m pip install "torch==${TORCH_VER}" --index-url "https://download.pytorch.org/whl/${CU_TAG}" --force-reinstall - python3 -m pip install numpy - python3 -m pip install dist/*.whl - python3 -c "import deep_gemm; print('deep_gemm:', deep_gemm.__file__)" - - - name: Run DeepGEMM test suite - run: | - chmod +x "${{ github.workspace }}/DeepGEMM/sgl_deep_gemm/run_tests.sh" - "${{ github.workspace }}/DeepGEMM/sgl_deep_gemm/run_tests.sh" - release-cu129: - needs: [build-cu129-matrix, test-cu129] + needs: build-cu129-matrix runs-on: ubuntu-latest steps: - uses: actions/checkout@v4