[Deps] Retire the CUDA 12 lane (#38404)

Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
This commit is contained in:
Mohammad Miadh Angkad
2026-09-10 16:58:09 -07:00
committed by GitHub
co-authored by Mohammad Angkad
parent fae8cd84cb
commit 52c191da52
38 changed files with 170 additions and 737 deletions
-105
View File
@@ -15,7 +15,6 @@ on:
default: 'all'
options:
- 'all'
- 'cu129'
- 'cu130'
- 'rocm700'
- 'rocm720'
@@ -35,110 +34,6 @@ concurrency:
cancel-in-progress: true
jobs:
# cu130 is the PyPI-released variant; cu129 wheels are published only to the
# sgl-project/whl index (consumed via `pip install ...+cu129` for the legacy
# cuda 12.9 path), not to PyPI.
build-cu129-matrix:
if: |
github.repository == 'sgl-project/sglang' &&
(github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu129')
strategy:
matrix:
python-version: ["3.10"]
cuda-version: ["12.9"]
arch: [x86_64, aarch64]
include:
- arch: x86_64
runner: x64-kernel-build-node
- arch: aarch64
runner: arm-kernel-build-node
runs-on: ${{ matrix.runner }}
steps:
# Self-hosted build nodes retain the workspace across jobs. Prior builds
# leave root-owned artifacts under python/sglang/kernels/aot/build/ that actions/checkout
# cannot remove, causing EACCES on rmdir. Wipe them via a throwaway root
# container before checkout recreates the workspace.
- name: Clean workspace (remove root-owned files from prior runs)
run: |
docker run --rm -v "${{ github.workspace }}:/workspace" alpine:3 \
sh -c 'rm -rf /workspace/..?* /workspace/.[!.]* /workspace/*' || true
- uses: actions/checkout@v4
with:
submodules: "recursive"
ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Build wheels
run: |
cd python/sglang/kernels/aot
chmod +x ./build.sh
./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}" ${{ matrix.arch == 'aarch64' && 'aarch64' || '' }}
env:
BUILD_JOBS: 64
NVCC_THREADS: 8
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}${{ matrix.arch == 'aarch64' && '-aarch64' || '' }}
path: python/sglang/kernels/aot/dist/*
release-cu129:
needs: build-cu129-matrix
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || '' }}
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: python/sglang/kernels/aot/dist/
merge-multiple: true
pattern: wheel-*
- name: Set tag name
id: set_tag_name
run: |
if [ -z "${{ inputs.tag_name }}" ]; then
TAG_NAME="v$(cat python/sglang/kernels/aot/python/sgl_kernel/version.py | cut -d'"' -f2)"
echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
else
echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
fi
- name: Release
uses: softprops/action-gh-release@v2
with:
tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
python/sglang/kernels/aot/dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
env:
WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
- name: Update wheel index
run: python3 scripts/update_kernel_whl_index.py --cuda 129
- name: Push wheel index
run: |
cd sgl-whl
git config --local user.name "sglang-bot"
git config --local user.email "sglangbot@gmail.com"
git add -A
git commit -m "update whl index"
git push
build-cu130-matrix:
if: |
github.repository == 'sgl-project/sglang' &&