EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[NVIDIA] Build CUDA 13 (#11299)

Browse Source 
Co-authored-by: ishandhanani <ishandhanani@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
This commit is contained in:
Johnny
2025-10-22 20:03:12 -07:00
committed by GitHub
parent 4d4feccbb2
commit e7aa4664b3
6 changed files with 131 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.github/workflows/release-whl-kernel.yml vendored
View File

@@ -17,13 +17,18 @@ concurrency:
cancel-in-progress: true
jobs:
build-cu129:
build-cu129-matrix:
if: github.repository == 'sgl-project/sglang'
runs-on: x64-kernel-build-node
strategy:
matrix:
python-version: ["3.10"]
cuda-version: ["12.9"]
include:
- arch: x86_64
runner: x64-kernel-build-node
- arch: aarch64
runner: arm-kernel-build-node
runs-on: ${{ matrix.runner }}
steps:
- uses: actions/checkout@v4
with:
@@ -38,7 +43,7 @@ jobs:
run: |
cd sgl-kernel
chmod +x ./build.sh
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}"
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
- name: Upload to PyPI
working-directory: sgl-kernel
@@ -49,11 +54,11 @@ jobs:
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
path: sgl-kernel/dist/*
release-cu129:
needs: build-cu129
needs: build-cu129-matrix
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -101,13 +106,19 @@ jobs:
git commit -m "update whl index"
git push
build-cu129-aarch64:
# for now we do not release CUDA 13.0 wheels to pypi
build-cu130-matrix:
if: github.repository == 'sgl-project/sglang'
runs-on: arm-kernel-build-node
strategy:
matrix:
python-version: ["3.10"]
cuda-version: ["12.9"]
cuda-version: ["13.0"]
include:
- arch: x86_64
runner: x64-kernel-build-node
- arch: aarch64
runner: arm-kernel-build-node
runs-on: ${{ matrix.runner }}
steps:
- uses: actions/checkout@v4
with:
@@ -122,22 +133,16 @@ jobs:
run: |
cd sgl-kernel
chmod +x ./build.sh
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" aarch64
- name: Upload to PyPI
working-directory: sgl-kernel
run: |
pip install twine
python3 -m twine upload --skip-existing dist/* -u __token__ -p ${{ secrets.PYPI_TOKEN }}
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}-aarch64
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
path: sgl-kernel/dist/*
release-cu129-aarch64:
needs: build-cu129-aarch64
release-cu130:
needs: build-cu130-matrix
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
@@ -174,7 +179,7 @@ jobs:
WHL_TOKEN: ${{ secrets.WHL_TOKEN }}
- name: Update wheel index
run: python3 scripts/update_kernel_whl_index.py --cuda 129
run: python3 scripts/update_kernel_whl_index.py --cuda 130
- name: Push wheel index
run: |