minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/_docker-build-and-publish.yml
+21 -92
View File
@@ -1,7 +1,7 @@
name: Build and Publish Multi-Arch Docker Images
# Reusable workflow: builds CUDA 12 + CUDA 13 images for amd64 and arm64,
# then creates multi-arch manifests with caller-specified tags.
# Reusable workflow: builds CUDA 13 images for amd64 and arm64, then creates
# multi-arch manifests with caller-specified tags.
on:
workflow_call:
@@ -26,7 +26,7 @@ on:
type: string
default: ""
tag_config:
description: 'JSON array of {"cuda":"cu129|cu130","tags":["tag1","tag2"]}. Tags support {version} substitution.'
description: 'JSON array of {"cuda":"cu130","tags":["tag1","tag2"]}. Tags support {version} substitution.'
required: true
type: string
use_environment:
@@ -50,7 +50,6 @@ jobs:
SGL_VERSION: ${{ inputs.sgl_version }}
IMAGE_REPO: ${{ inputs.image_repo }}
outputs:
digest-cu129: ${{ steps.build-cu129.outputs.digest }}
digest-cu130: ${{ steps.build-cu130.outputs.digest }}
steps:
- name: Delete huge unnecessary tools folder
@@ -69,16 +68,14 @@ jobs:
set -euo pipefail
BUILD_COMMIT="$(git rev-parse HEAD)"
BUILD_URL="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
for CUDA_VARIANT in cu129 cu130; do
python3 scripts/ci/utils/docker_build_metadata_args.py \
--cuda "${CUDA_VARIANT}" \
--tag-config "${TAG_CONFIG}" \
--image-repo "${IMAGE_REPO}" \
--sgl-version "${SGL_VERSION}" \
--build-commit "${BUILD_COMMIT}" \
--build-url "${BUILD_URL}" \
> "/tmp/docker-metadata-${CUDA_VARIANT}.args"
done
python3 scripts/ci/utils/docker_build_metadata_args.py \
--cuda cu130 \
--tag-config "${TAG_CONFIG}" \
--image-repo "${IMAGE_REPO}" \
--sgl-version "${SGL_VERSION}" \
--build-commit "${BUILD_COMMIT}" \
--build-url "${BUILD_URL}" \
> /tmp/docker-metadata-cu130.args
- name: Free disk space
uses: jlumbroso/free-disk-space@main
@@ -106,34 +103,6 @@ jobs:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Build and push AMD64 image (CUDA 12)
id: build-cu129
run: |
VERSION_ARG=""
if [ -n "${SGL_VERSION}" ]; then
VERSION_ARG="--build-arg SGL_VERSION=${SGL_VERSION}"
fi
mapfile -t METADATA_ARGS < /tmp/docker-metadata-cu129.args
docker buildx build \
--target ${{ inputs.docker_target }} \
--platform linux/amd64 \
--output type=image,name=${{ inputs.image_repo }},push-by-digest=true,name-canonical=true,push=true \
-f docker/Dockerfile \
--build-arg CUDA_VERSION=12.9.2 \
--build-arg BUILD_TYPE=all \
--build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
"${METADATA_ARGS[@]}" \
${VERSION_ARG} \
${{ inputs.extra_build_args }} \
--metadata-file /tmp/metadata-cu129.json \
--no-cache \
.
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129.json'))['containerimage.digest'])")
echo "Pushed digest: ${DIGEST}"
echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
- name: Build and push AMD64 image (CUDA 13)
id: build-cu130
run: |
@@ -171,7 +140,6 @@ jobs:
SGL_VERSION: ${{ inputs.sgl_version }}
IMAGE_REPO: ${{ inputs.image_repo }}
outputs:
digest-cu129: ${{ steps.build-cu129.outputs.digest }}
digest-cu130: ${{ steps.build-cu130.outputs.digest }}
steps:
- name: Delete huge unnecessary tools folder
@@ -190,16 +158,14 @@ jobs:
set -euo pipefail
BUILD_COMMIT="$(git rev-parse HEAD)"
BUILD_URL="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
for CUDA_VARIANT in cu129 cu130; do
python3 scripts/ci/utils/docker_build_metadata_args.py \
--cuda "${CUDA_VARIANT}" \
--tag-config "${TAG_CONFIG}" \
--image-repo "${IMAGE_REPO}" \
--sgl-version "${SGL_VERSION}" \
--build-commit "${BUILD_COMMIT}" \
--build-url "${BUILD_URL}" \
> "/tmp/docker-metadata-${CUDA_VARIANT}.args"
done
python3 scripts/ci/utils/docker_build_metadata_args.py \
--cuda cu130 \
--tag-config "${TAG_CONFIG}" \
--image-repo "${IMAGE_REPO}" \
--sgl-version "${SGL_VERSION}" \
--build-commit "${BUILD_COMMIT}" \
--build-url "${BUILD_URL}" \
> /tmp/docker-metadata-cu130.args
- name: Prune Docker to reclaim disk space
run: |
@@ -216,34 +182,6 @@ jobs:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Build and push ARM64 image (CUDA 12)
id: build-cu129
run: |
VERSION_ARG=""
if [ -n "${SGL_VERSION}" ]; then
VERSION_ARG="--build-arg SGL_VERSION=${SGL_VERSION}"
fi
mapfile -t METADATA_ARGS < /tmp/docker-metadata-cu129.args
docker buildx build \
--target ${{ inputs.docker_target }} \
--platform linux/arm64 \
--output type=image,name=${{ inputs.image_repo }},push-by-digest=true,name-canonical=true,push=true \
-f docker/Dockerfile \
--build-arg CUDA_VERSION=12.9.2 \
--build-arg BUILD_TYPE=all \
--build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
"${METADATA_ARGS[@]}" \
${VERSION_ARG} \
${{ inputs.extra_build_args }} \
--metadata-file /tmp/metadata-cu129.json \
--no-cache \
.
DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129.json'))['containerimage.digest'])")
echo "Pushed digest: ${DIGEST}"
echo "digest=${DIGEST}" >> $GITHUB_OUTPUT
- name: Build and push ARM64 image (CUDA 13)
id: build-cu130
run: |
@@ -292,22 +230,13 @@ jobs:
TAG_CONFIG: ${{ inputs.tag_config }}
SGL_VERSION: ${{ inputs.sgl_version }}
IMAGE_REPO: ${{ inputs.image_repo }}
X86_CU129: ${{ needs.build-x86.outputs.digest-cu129 }}
X86_CU130: ${{ needs.build-x86.outputs.digest-cu130 }}
ARM64_CU129: ${{ needs.build-arm64.outputs.digest-cu129 }}
ARM64_CU130: ${{ needs.build-arm64.outputs.digest-cu130 }}
SHORT_SHA: ${{ github.sha }}
run: |
echo "${TAG_CONFIG}" | jq -c '.[]' | while read -r entry; do
CUDA=$(echo "${entry}" | jq -r '.cuda')
if [ "${CUDA}" = "cu129" ]; then
X86_DIGEST="${X86_CU129}"
ARM64_DIGEST="${ARM64_CU129}"
else
X86_DIGEST="${X86_CU130}"
ARM64_DIGEST="${ARM64_CU130}"
fi
X86_DIGEST="${X86_CU130}"
ARM64_DIGEST="${ARM64_CU130}"
TAG_ARGS=""
for tag in $(echo "${entry}" | jq -r '.tags[]'); do
.github/workflows/patch-docker-dev.yml
+1 -1
View File
@@ -8,7 +8,7 @@ on:
required: false
default: ""
image_tag:
description: "Base image tag to patch (e.g. dev, dev-cu13, dev-cu12)"
description: "Base image tag to patch (e.g. dev, dev-cu13)"
required: true
output_tag:
description: "Tag to publish as. Overwrites it if it already exists."
.github/workflows/release-docker-dev.yml
+6 -8
View File
@@ -25,7 +25,7 @@ on:
required: false
default: ""
overlay_cudas:
description: "Comma-separated cuda variants to overlay onto (cu12, cu13). Default 'cu13'."
description: "Comma-separated cuda variants to overlay onto (cu13). Default 'cu13'."
required: false
default: "cu13"
overlay_tag_suffix:
@@ -86,9 +86,9 @@ jobs:
# consumers pinned to the pre-flip names.
if [ -z "${SUFFIX}" ]; then
# Nightly: include dated tags
TAG_CONFIG='[{"cuda":"cu129","tags":["dev-cu12","nightly-dev-cu12-{date}-{short_sha}"]},{"cuda":"cu130","tags":["dev","dev-cu13","nightly-dev-{date}-{short_sha}","nightly-dev-cu13-{date}-{short_sha}"]}]'
TAG_CONFIG='[{"cuda":"cu130","tags":["dev","dev-cu13","nightly-dev-{date}-{short_sha}","nightly-dev-cu13-{date}-{short_sha}"]}]'
else
TAG_CONFIG="[{\"cuda\":\"cu129\",\"tags\":[\"dev-cu12${SUFFIX}\"]},{\"cuda\":\"cu130\",\"tags\":[\"dev${SUFFIX}\",\"dev-cu13${SUFFIX}\"]}]"
TAG_CONFIG="[{\"cuda\":\"cu130\",\"tags\":[\"dev${SUFFIX}\",\"dev-cu13${SUFFIX}\"]}]"
fi
echo "tag_config=${TAG_CONFIG}" >> $GITHUB_OUTPUT
@@ -97,7 +97,7 @@ jobs:
# SUFFIX was computed above from inputs.tag / inputs.pr_number.
if [ -n "${OVERLAY_DOCKERFILE_INPUT}" ]; then
# Refuse to overlay without a tag/pr_number: SUFFIX would be empty,
# so base would point at the moving 'dev'/'dev-cu12'/'dev-cu13'
# so base would point at the moving 'dev'/'dev-cu13'
# latest tags and overwrite mode would clobber them.
if [ -z "${SUFFIX}" ]; then
echo "overlay_dockerfile is set but neither 'tag' nor 'pr_number' was given." >&2
@@ -112,10 +112,8 @@ jobs:
C="$(echo "${C}" | xargs)"
if [ "${C}" = "cu13" ]; then
BASES='["dev'"${SUFFIX}"'","dev-cu13'"${SUFFIX}"'"]'
elif [ "${C}" = "cu12" ]; then
BASES='["dev-cu12'"${SUFFIX}"'"]'
else
echo "Unknown overlay cuda variant: ${C} (expected cu12 or cu13)" >&2
echo "Unknown overlay cuda variant: ${C} (expected cu13)" >&2
exit 1
fi
if [ -n "${OVERLAY_SUFFIX_INPUT}" ]; then
@@ -213,7 +211,7 @@ jobs:
if: ${{ !inputs.build_only && !inputs.tag && !inputs.pr_number }}
uses: ./.github/workflows/_docker-cleanup-nightly.yml
with:
tag_prefixes: '["nightly-dev", "nightly-dev-cu12", "nightly-dev-cu13"]'
tag_prefixes: '["nightly-dev", "nightly-dev-cu13"]'
image_repo: ${{ inputs.image_repo || 'lmsysorg/sglang' }}
secrets: inherit
.github/workflows/release-docker-runtime.yml
+2 -3
View File
@@ -2,7 +2,7 @@ name: Release Docker Runtime Images
#
# Builds and publishes runtime Docker images (production-optimized, ~50% smaller):
# - lmsysorg/sglang:v{version}-runtime, lmsysorg/sglang:latest-runtime
# - lmsysorg/sglang:v{version}-cu129-runtime, lmsysorg/sglang:latest-cu129-runtime
# - lmsysorg/sglang:v{version}-cu130-runtime, lmsysorg/sglang:latest-cu130-runtime
#
on:
push:
@@ -49,7 +49,6 @@ jobs:
image_repo: ${{ inputs.image_repo || 'lmsysorg/sglang' }}
tag_config: |
[
{"cuda": "cu130", "tags": ["v${{ needs.resolve-version.outputs.version }}-runtime", "latest-runtime", "v${{ needs.resolve-version.outputs.version }}-cu130-runtime", "latest-cu130-runtime"]},
{"cuda": "cu129", "tags": ["v${{ needs.resolve-version.outputs.version }}-cu129-runtime", "latest-cu129-runtime"]}
{"cuda": "cu130", "tags": ["v${{ needs.resolve-version.outputs.version }}-runtime", "latest-runtime", "v${{ needs.resolve-version.outputs.version }}-cu130-runtime", "latest-cu130-runtime"]}
]
secrets: inherit
.github/workflows/release-docker.yml
+2 -3
View File
@@ -2,7 +2,7 @@ name: Release Docker Images
#
# Builds and publishes framework Docker images (full development environment):
# - lmsysorg/sglang:v{version}, lmsysorg/sglang:latest (cuda 13)
# - lmsysorg/sglang:v{version}-cu129, lmsysorg/sglang:latest-cu129
# - lmsysorg/sglang:v{version}-cu130, lmsysorg/sglang:latest-cu130
#
on:
push:
@@ -49,7 +49,6 @@ jobs:
image_repo: ${{ inputs.image_repo || 'lmsysorg/sglang' }}
tag_config: |
[
{"cuda": "cu130", "tags": ["v${{ needs.resolve-version.outputs.version }}", "latest", "v${{ needs.resolve-version.outputs.version }}-cu130", "latest-cu130"]},
{"cuda": "cu129", "tags": ["v${{ needs.resolve-version.outputs.version }}-cu129", "latest-cu129"]}
{"cuda": "cu130", "tags": ["v${{ needs.resolve-version.outputs.version }}", "latest", "v${{ needs.resolve-version.outputs.version }}-cu130", "latest-cu130"]}
]
secrets: inherit
.github/workflows/release-pypi-nightly.yml
+5 -5
View File
@@ -113,13 +113,13 @@ jobs:
environment: 'prod'
strategy:
fail-fast: false
# The wheel is CUDA-agnostic and built once — we just register the same
# artifact under cu129/sglang/ and cu130/sglang/ wheel indexes so users
# can install via either --extra-index-url. Serialize because both matrix
# runs clone and push to the same sgl-whl branch.
# The wheel is CUDA-agnostic and built once — we just register it under
# the cu130/sglang/ wheel index so users can install via
# --extra-index-url. Serialize because matrix runs clone and push to the
# same sgl-whl branch.
max-parallel: 1
matrix:
cuda_version: ['129', '130']
cuda_version: ['130']
steps:
- uses: actions/checkout@v4
.github/workflows/release-whl-deepep.yml
+7 -103
View File
@@ -7,15 +7,6 @@ on:
description: "Public wheel version (for example, 0.1.0 or 0.1.1rc0)"
type: string
required: true
target:
description: "CUDA target"
type: choice
required: false
default: "all"
options:
- "all"
- "cu129"
- "cu130"
packaging-ref:
description: "DeepEP ref containing the shared sgl_deep_ep overlay"
type: string
@@ -30,75 +21,8 @@ env:
TORCH_VERSION: "2.13.0"
jobs:
build-cu129-matrix:
if: |
github.repository == 'sgl-project/sglang' &&
(inputs.target == 'all' || inputs.target == 'cu129')
strategy:
fail-fast: false
matrix:
python-version: ["3.10", "3.12"]
arch: [x86_64, aarch64]
include:
- arch: x86_64
runner: x64-kernel-build-node
source-branch: sgl-deepep-cu12-x86
- arch: aarch64
runner: arm-kernel-build-node
source-branch: sgl-deepep-cu12-arm
runs-on: ${{ matrix.runner }}
steps:
- name: Clean workspace
run: |
docker run --rm -v "${{ github.workspace }}:/workspace" alpine:3 \
sh -c 'rm -rf /workspace/..?* /workspace/.[!.]* /workspace/*' || true
- name: Checkout SGLang
uses: actions/checkout@v4
- name: Checkout DeepEP implementation
uses: actions/checkout@v4
with:
repository: sgl-project/DeepEP
ref: ${{ matrix.source-branch }}
path: DeepEP-source
submodules: recursive
- name: Checkout DeepEP packaging overlay
uses: actions/checkout@v4
with:
repository: sgl-project/DeepEP
ref: ${{ inputs['packaging-ref'] || 'sgl-deepep-packaging' }}
path: DeepEP-packaging
sparse-checkout: sgl_deep_ep
- name: Set wheel version
env:
RELEASE_VERSION: ${{ inputs.version }}
run: |
printf '%s' "${RELEASE_VERSION}" > DeepEP-packaging/sgl_deep_ep/VERSION
- name: Build wheel
run: |
chmod +x scripts/build_sgl_deepep.sh DeepEP-packaging/sgl_deep_ep/build_sgl_deep_ep.sh
scripts/build_sgl_deepep.sh \
"${{ matrix.python-version }}" \
"12.9" \
"${{ github.workspace }}/DeepEP-source" \
"${{ github.workspace }}/DeepEP-packaging/sgl_deep_ep" \
"${{ matrix.arch }}"
- name: Upload wheel
uses: actions/upload-artifact@v4
with:
name: deepep-wheel-cu129-py${{ matrix.python-version }}-${{ matrix.arch }}
path: DeepEP-source/dist/*.whl
if-no-files-found: error
build-cu130-matrix:
if: |
github.repository == 'sgl-project/sglang' &&
(inputs.target == 'all' || inputs.target == 'cu130')
if: github.repository == 'sgl-project/sglang'
strategy:
fail-fast: false
matrix:
@@ -168,19 +92,10 @@ jobs:
if-no-files-found: error
release-whl:
needs: [build-cu129-matrix, build-cu130-matrix]
needs: build-cu130-matrix
if: |
always() &&
github.repository == 'sgl-project/sglang' &&
(
(inputs.target == 'cu129' && needs.build-cu129-matrix.result == 'success') ||
(inputs.target == 'cu130' && needs.build-cu130-matrix.result == 'success') ||
(
inputs.target == 'all' &&
needs.build-cu129-matrix.result == 'success' &&
needs.build-cu130-matrix.result == 'success'
)
)
needs.build-cu130-matrix.result == 'success'
runs-on: ubuntu-latest
steps:
- name: Checkout SGLang
@@ -209,14 +124,8 @@ jobs:
git clone --branch gh-pages \
"https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git" sgl-whl
- name: Update wheel indexes
run: |
if [[ "${{ inputs.target }}" == "all" || "${{ inputs.target }}" == "cu129" ]]; then
python3 scripts/update_deepep_whl_index.py --cuda 129
fi
if [[ "${{ inputs.target }}" == "all" || "${{ inputs.target }}" == "cu130" ]]; then
python3 scripts/update_deepep_whl_index.py --cuda 130
fi
- name: Update wheel index
run: python3 scripts/update_deepep_whl_index.py --cuda 130
- name: Push wheel indexes
env:
@@ -234,15 +143,10 @@ jobs:
fi
release-pypi:
needs: [build-cu129-matrix, build-cu130-matrix]
needs: build-cu130-matrix
if: |
always() &&
github.repository == 'sgl-project/sglang' &&
needs.build-cu130-matrix.result == 'success' &&
(
inputs.target == 'cu130' ||
(inputs.target == 'all' && needs.build-cu129-matrix.result == 'success')
)
needs.build-cu130-matrix.result == 'success'
runs-on: ubuntu-latest
steps:
- name: Download PyPI wheels
.github/workflows/release-whl-deepgemm.yml
-87
View File
@@ -14,7 +14,6 @@ on:
default: 'all'
options:
- 'all'
- 'cu129'
- 'cu130'
branch:
description: "DeepGEMM branch to build from (default: dev)"
@@ -33,92 +32,6 @@ env:
TORCH_VER: "2.13.0"
jobs:
build-cu129-matrix:
if: |
github.repository == 'sgl-project/sglang' &&
(github.event.inputs.target == 'all' || github.event.inputs.target == 'cu129')
strategy:
matrix:
python-version: ["3.12"]
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: ${{ matrix.runner }}
steps:
- name: Clean workspace (remove root-owned files from prior runs)
run: |
docker run --rm -v "${{ github.workspace }}:/workspace" alpine:3 \
sh -c 'rm -rf /workspace/..?* /workspace/.[!.]* /workspace/*' || true
- uses: actions/checkout@v4
- name: Checkout DeepGEMM
uses: actions/checkout@v4
with:
repository: sgl-project/DeepGEMM
ref: ${{ inputs.branch || 'dev' }}
path: DeepGEMM
submodules: recursive
- name: Set wheel version
run: |
echo -n "${{ inputs.version }}" > DeepGEMM/sgl_deep_gemm/VERSION
cat DeepGEMM/sgl_deep_gemm/VERSION
- name: Build wheel
run: |
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 artifacts
uses: actions/upload-artifact@v4
with:
name: deepgemm-wheel-cuda${{ matrix.cuda-version }}-${{ matrix.arch }}
path: DeepGEMM/dist/*.whl
release-cu129:
needs: build-cu129-matrix
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist/
merge-multiple: true
pattern: deepgemm-wheel-cuda12.9-*
- name: Release
uses: softprops/action-gh-release@v2
with:
tag_name: v${{ inputs.version }}
repository: sgl-project/whl
token: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
files: |
dist/*
- name: Clone wheel index
run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
env:
WHL_TOKEN: ${{ secrets.GH_PAT_FOR_WHL_RELEASE }}
- name: Update wheel index
run: python3 scripts/update_deepgemm_whl_index.py --cuda 129
- name: Push wheel index
run: |
cd sgl-whl
git config --local user.name "sglang-bot"
git config --local user.email "sglangbot@gmail.com"
git add -A
git commit -m "update sgl-deep-gemm whl index for v${{ inputs.version }}"
git push
build-cu130-matrix:
if: |
github.repository == 'sgl-project/sglang' &&
.github/workflows/release-whl-kernel.yml
-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' &&
.github/workflows/retag-docker.yml
+1 -1
View File
@@ -4,7 +4,7 @@ on:
workflow_dispatch:
inputs:
source_tag:
description: "Existing image tag (e.g., v0.4.7-cu129-amd64)"
description: "Existing image tag (e.g., v0.4.7-cu130-amd64)"
required: true
target_tag:
description: "New tag to apply (e.g., latest)"
.github/workflows/trivy-scan-dev.yml
+1 -1
View File
@@ -22,7 +22,7 @@ jobs:
strategy:
fail-fast: false
matrix:
tag: ${{ inputs.tag && fromJSON(format('["{0}"]', inputs.tag)) || fromJSON('["dev", "dev-cu12"]') }}
tag: ${{ inputs.tag && fromJSON(format('["{0}"]', inputs.tag)) || fromJSON('["dev", "dev-cu13"]') }}
steps:
- name: Cleanup workspace (remove root-owned files from prior runs)
run: sudo rm -rf "$GITHUB_WORKSPACE"/* || true