Mooncake/.github/workflows/pre-release.yaml

357 lines
12 KiB
YAML

name: Pre-Release
# Dry-run of the release pipelines: build wheels like Release / Release Non-CUDA /
# Release CUDA 13, validate artifacts, but do not create a GitHub Release or publish to PyPI.
#
# Trigger by pushing a pre-release tag, for example:
# git tag v1.0.0-rc1 && git push origin v1.0.0-rc1
on:
push:
tags:
- 'v*-rc*'
- 'v*-alpha*'
- 'v*-beta*'
- 'v*-pre*'
env:
SCCACHE_GHA_ENABLED: "true"
jobs:
build-cuda:
name: Build (CUDA 12)
runs-on: ubuntu-22.04
permissions:
contents: read
strategy:
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13']
env:
BUILD_WITH_EP: "1"
TORCH_CUDA_ARCH_LIST: "8.0;9.0"
steps:
- name: Checkout source
uses: actions/checkout@v4
- name: Set version from tag
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Free up disk space
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
df -h
- name: Install CUDA Toolkit
uses: Jimver/cuda-toolkit@v0.2.24
with:
cuda: '12.8.1'
linux-local-args: '["--toolkit"]'
method: 'network'
sub-packages: '["nvcc", "nvrtc-dev"]'
non-cuda-sub-packages: '["libcusparse-dev", "libcublas-dev", "libcusolver-dev"]'
- name: Run sccache-cache
uses: mozilla-actions/sccache-action@v0.0.9
- name: Configure sccache
uses: actions/github-script@v7
with:
script: |
core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || '');
core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
- name: Configure project
run: |
sudo apt update -y
sudo bash -x dependencies.sh -y
mkdir build
cd build
cmake .. -DBUILD_UNIT_TESTS=OFF -DUSE_HTTP=ON -DUSE_ETCD=ON -DUSE_CUDA=ON -DWITH_EP=ON -DEP_TORCH_VERSIONS="2.9.1;2.10.0;2.11.0;2.12.0" -DSTORE_USE_ETCD=ON -DENABLE_SCCACHE=ON -DCMAKE_BUILD_TYPE=Release
shell: bash
- name: Build project
run: |
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
cd build
make -j
sudo -E make install
shell: bash
- name: Build nvlink_allocator.so
run: |
export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
mkdir -p build/mooncake-transfer-engine/nvlink-allocator
cd mooncake-transfer-engine/nvlink-allocator
bash build.sh ../../build/mooncake-transfer-engine/nvlink-allocator/
shell: bash
- name: Run sccache stat for check
if: ${{ env.SCCACHE_PATH != '' }}
shell: bash
run: ${SCCACHE_PATH} --show-stats
- name: Generate Python version tag
id: generate_tag_release
run: |
echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT
shell: bash
- name: Build Python wheel
run: |
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag_release.outputs.python_version_tag }} ./scripts/build_wheel.sh
env:
VERSION: ${{ env.VERSION }}
- name: Upload Python wheel artifact
uses: actions/upload-artifact@v4
with:
name: pre-release-cuda-py${{ steps.generate_tag_release.outputs.python_version_tag }}
path: mooncake-wheel/dist-py${{ steps.generate_tag_release.outputs.python_version_tag }}/*.whl
build-non-cuda:
name: Build (Non-CUDA)
runs-on: ubuntu-22.04
permissions:
contents: read
strategy:
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13']
env:
BUILD_WITH_EP: "0"
NON_CUDA_BUILD: "1"
steps:
- name: Checkout source
uses: actions/checkout@v4
- name: Set version from tag
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Free up disk space
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL
- name: Run sccache-cache
uses: mozilla-actions/sccache-action@v0.0.9
- name: Configure sccache
uses: actions/github-script@v7
with:
script: |
core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || '');
core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
- name: Configure project
run: |
sudo apt update -y
sudo bash -x dependencies.sh -y
mkdir build
cd build
cmake .. -DUSE_HTTP=ON -DUSE_ETCD=ON -DUSE_CUDA=OFF -DWITH_EP=OFF -DSTORE_USE_ETCD=ON -DENABLE_SCCACHE=ON -DCMAKE_BUILD_TYPE=Release
shell: bash
- name: Build project
run: |
cd build
make -j
sudo make install
shell: bash
- name: Run sccache stat for check
if: ${{ env.SCCACHE_PATH != '' }}
shell: bash
run: ${SCCACHE_PATH} --show-stats
- name: Generate Python version tag
id: generate_tag_release
run: |
echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT
shell: bash
- name: Build Python wheel
run: |
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag_release.outputs.python_version_tag }} ./scripts/build_wheel.sh
env:
VERSION: ${{ env.VERSION }}
- name: Upload Python wheel artifact
uses: actions/upload-artifact@v4
with:
name: pre-release-non-cuda-py${{ steps.generate_tag_release.outputs.python_version_tag }}
path: mooncake-wheel/dist-py${{ steps.generate_tag_release.outputs.python_version_tag }}/*.whl
build-cuda13:
name: Build (CUDA 13)
runs-on: ubuntu-22.04
permissions:
contents: read
strategy:
matrix:
python-version: ['3.10', '3.11', '3.12', '3.13']
env:
BUILD_WITH_EP: "1"
CU13_BUILD: "1"
TORCH_CUDA_ARCH_LIST: "8.0;9.0"
steps:
- name: Checkout source
uses: actions/checkout@v4
- name: Set version from tag
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Free up disk space
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
df -h
- name: Install CUDA Toolkit 13
uses: Jimver/cuda-toolkit@v0.2.29
with:
cuda: '13.0.2'
linux-local-args: '["--toolkit"]'
method: 'network'
sub-packages: '["nvcc", "nvrtc-dev"]'
non-cuda-sub-packages: '["libcusparse-dev", "libcublas-dev", "libcusolver-dev"]'
- name: Run sccache-cache
uses: mozilla-actions/sccache-action@v0.0.9
- name: Configure sccache
uses: actions/github-script@v7
with:
script: |
core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || '');
core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
- name: Configure project
run: |
sudo apt update -y
sudo bash -x dependencies.sh -y
mkdir build
cd build
cmake .. -DBUILD_UNIT_TESTS=OFF -DUSE_HTTP=ON -DUSE_ETCD=ON -DUSE_CUDA=ON -DWITH_EP=ON -DEP_TORCH_VERSIONS="2.9.0;2.9.1;2.10.0;2.11.0" -DSTORE_USE_ETCD=ON -DENABLE_SCCACHE=ON -DCMAKE_BUILD_TYPE=Release
shell: bash
- name: Build project
run: |
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
cd build
make -j
sudo make install
shell: bash
- name: Build nvlink_allocator.so
run: |
export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
mkdir -p build/mooncake-transfer-engine/nvlink-allocator
cd mooncake-transfer-engine/nvlink-allocator
bash build.sh ../../build/mooncake-transfer-engine/nvlink-allocator/
shell: bash
- name: Run sccache stat for check
if: ${{ env.SCCACHE_PATH != '' }}
shell: bash
run: ${SCCACHE_PATH} --show-stats
- name: Generate Python version tag
id: generate_tag_release
run: |
echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT
shell: bash
- name: Build Python wheel
run: |
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag_release.outputs.python_version_tag }} ./scripts/build_wheel.sh
env:
VERSION: ${{ env.VERSION }}
- name: Upload Python wheel artifact
uses: actions/upload-artifact@v4
with:
name: pre-release-cuda13-py${{ steps.generate_tag_release.outputs.python_version_tag }}
path: mooncake-wheel/dist-py${{ steps.generate_tag_release.outputs.python_version_tag }}/*.whl
validate-release:
name: Validate release artifacts
needs: [build-cuda, build-non-cuda, build-cuda13]
runs-on: ubuntu-22.04
permissions:
contents: read
steps:
- name: Checkout source
uses: actions/checkout@v4
- name: Download all pre-release wheel artifacts
uses: actions/download-artifact@v4
with:
path: mooncake-wheel/dist-all
pattern: pre-release-*
- name: Prepare wheels for validation
run: |
mkdir -p mooncake-wheel/dist-release
find mooncake-wheel/dist-all -name "*.whl" -exec cp {} mooncake-wheel/dist-release/ \;
echo "Pre-release tag: ${GITHUB_REF_NAME}"
echo "Collected wheels:"
ls -la mooncake-wheel/dist-release/
wheel_count=$(find mooncake-wheel/dist-release -name "*.whl" | wc -l)
echo "wheel_count=${wheel_count}" >> "$GITHUB_ENV"
if [ "${wheel_count}" -lt 12 ]; then
echo "Expected at least 12 wheels (4 Python versions x 3 variants), found ${wheel_count}"
exit 1
fi
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.12'
- name: Validate wheels with twine
run: |
pip install twine
twine check mooncake-wheel/dist-release/*.whl
- name: Upload validated wheels as workflow artifacts
uses: actions/upload-artifact@v4
with:
name: pre-release-wheels-${{ github.ref_name }}
path: mooncake-wheel/dist-release/*.whl
retention-days: 14
- name: Pre-release validation summary
run: |
echo "## Pre-Release validation passed" >> "$GITHUB_STEP_SUMMARY"
echo "" >> "$GITHUB_STEP_SUMMARY"
echo "- Tag: \`${GITHUB_REF_NAME}\`" >> "$GITHUB_STEP_SUMMARY"
echo "- Wheels built: ${wheel_count}" >> "$GITHUB_STEP_SUMMARY"
echo "- PyPI publish: skipped (pre-release dry run)" >> "$GITHUB_STEP_SUMMARY"
echo "- GitHub Release upload: skipped (pre-release dry run)" >> "$GITHUB_STEP_SUMMARY"