minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Add DeepGEMM prerelease wheel tests (#27075)

Browse Source 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-06-11 15:14:50 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent d71e9bede6
commit 493f828bfa
1 changed files with 129 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/release-whl-deepgemm.yml
+129 -10
View File
@@ -26,6 +26,11 @@ concurrency:
group: release-sgl-deepgemm-${{ github.ref }}
cancel-in-progress: true
env:
# Must match TORCH_VER in docker/sgl-deep-gemm.Dockerfile — the wheel's
# pre-compiled _C.so links against this torch ABI.
TORCH_VER: "2.11.0"
jobs:
build-cu129-matrix:
if: |
@@ -54,7 +59,7 @@ jobs:
uses: actions/checkout@v4
with:
repository: sgl-project/DeepGEMM
ref: ${{ inputs.branch }}
ref: ${{ inputs.branch || 'dev' }}
path: DeepGEMM
submodules: recursive
@@ -74,8 +79,57 @@ jobs:
name: deepgemm-wheel-cuda${{ matrix.cuda-version }}-${{ matrix.arch }}
path: DeepGEMM/dist/*.whl
release-cu129:
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]
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -140,7 +194,7 @@ jobs:
uses: actions/checkout@v4
with:
repository: sgl-project/DeepGEMM
ref: ${{ inputs.branch }}
ref: ${{ inputs.branch || 'dev' }}
path: DeepGEMM
submodules: recursive
@@ -159,20 +213,73 @@ jobs:
chmod +x ./scripts/build_sgl_deep_gemm.sh ./scripts/rename_sgl_deep_gemm_whl.sh
./scripts/build_sgl_deep_gemm.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" "${{ github.workspace }}/DeepGEMM" "${{ matrix.arch }}"
- name: Upload to PyPI
working-directory: DeepGEMM
run: |
pip install twine
python3 -m twine upload --skip-existing dist-pypi/* -u __token__ -p ${{ secrets.SGL_DEEP_GEMM_PYPI_TOKEN }}
# PyPI upload moved to release-cu130 so it is gated on test-cu130.
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: deepgemm-wheel-cuda${{ matrix.cuda-version }}-${{ matrix.arch }}
path: DeepGEMM/dist/*.whl
release-cu130:
- name: Upload PyPI artifacts
uses: actions/upload-artifact@v4
with:
name: deepgemm-pypi-cuda${{ matrix.cuda-version }}-${{ matrix.arch }}
path: DeepGEMM/dist-pypi/*.whl
test-cu130:
needs: build-cu130-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
- arch_label: sm100-aarch64
runner: 4-gpu-gb300
wheel_arch: aarch64
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: ${{ inputs.branch || 'dev' }}
path: DeepGEMM
submodules: recursive
- name: Download wheel
uses: actions/download-artifact@v4
with:
path: dist/
merge-multiple: true
pattern: deepgemm-wheel-cuda13.0-${{ matrix.wheel_arch }}
- name: Install wheel and deps
env:
CU_TAG: cu130
run: |
python3 -m pip install --upgrade pip
# deep_gemm imports torch before loading _C.so, so torch must preload the
# libcudart the cu130 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-cu130:
needs: [build-cu130-matrix, test-cu130]
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -184,6 +291,18 @@ jobs:
merge-multiple: true
pattern: deepgemm-wheel-cuda13.0-*
- name: Download PyPI artifacts
uses: actions/download-artifact@v4
with:
path: dist-pypi/
merge-multiple: true
pattern: deepgemm-pypi-cuda13.0-*
- name: Upload to PyPI
run: |
pip install --upgrade twine "packaging>=24.2"
python3 -m twine upload --skip-existing dist-pypi/* -u __token__ -p ${{ secrets.SGL_DEEP_GEMM_PYPI_TOKEN }}
- name: Release
uses: softprops/action-gh-release@v2
with: