127 lines
3.8 KiB
YAML
127 lines
3.8 KiB
YAML
name: 'Build Wheel (CUDA 13)'
|
|
|
|
on:
|
|
workflow_call: {}
|
|
|
|
jobs:
|
|
build-wheel-cu13:
|
|
runs-on: ubuntu-22.04
|
|
strategy:
|
|
matrix:
|
|
python-version: ['3.10', '3.12']
|
|
env:
|
|
BUILD_WITH_EP: "1"
|
|
CU13_BUILD: "1"
|
|
TORCH_CUDA_ARCH_LIST: "8.0;9.0"
|
|
SCCACHE_GHA_ENABLED: "true"
|
|
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Set up Python ${{ matrix.python-version }}
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
|
|
- name: Free up disk space
|
|
run: |
|
|
sudo rm -rf /usr/share/dotnet
|
|
sudo rm -rf /opt/ghc
|
|
sudo rm -rf /opt/hostedtoolcache/CodeQL
|
|
sudo rm -rf /usr/local/lib/android
|
|
df -h
|
|
|
|
- name: Install CUDA Toolkit
|
|
uses: Jimver/cuda-toolkit@v0.2.29
|
|
with:
|
|
cuda: '13.0.2'
|
|
linux-local-args: '["--toolkit"]'
|
|
method: 'network'
|
|
sub-packages: '["nvcc", "nvrtc-dev"]'
|
|
non-cuda-sub-packages: '["libcusparse-dev", "libcublas-dev", "libcusolver-dev"]'
|
|
|
|
- name: Run sccache-cache
|
|
uses: mozilla-actions/sccache-action@v0.0.9
|
|
|
|
- name: Configure sccache
|
|
uses: actions/github-script@v7
|
|
with:
|
|
script: |
|
|
core.exportVariable('ACTIONS_RESULTS_URL', process.env.ACTIONS_RESULTS_URL || '');
|
|
core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
sudo apt update -y
|
|
sudo apt install -y ninja-build
|
|
sudo bash -x dependencies.sh -y
|
|
df -h
|
|
shell: bash
|
|
|
|
- name: Configure project
|
|
run: |
|
|
mkdir build
|
|
cd build
|
|
cmake -G Ninja .. \
|
|
-DUSE_ETCD=ON \
|
|
-DUSE_REDIS=ON \
|
|
-DUSE_HTTP=ON \
|
|
-DWITH_STORE=ON \
|
|
-DWITH_P2P_STORE=ON \
|
|
-DWITH_EP=ON \
|
|
-DEP_TORCH_VERSIONS="2.9.1;2.10.0;2.11.0;2.12.0" \
|
|
-DWITH_METRICS=ON \
|
|
-DBUILD_UNIT_TESTS=OFF \
|
|
-DBUILD_EXAMPLES=ON \
|
|
-DENABLE_SCCACHE=ON \
|
|
-DBUILD_BENCHMARK=ON \
|
|
-DUSE_CUDA=ON \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DCMAKE_EXE_LINKER_FLAGS="-L/usr/local/cuda/lib64/stubs" \
|
|
-DENABLE_DEBUG_SYMBOLS=OFF
|
|
shell: bash
|
|
|
|
- name: Build project
|
|
run: |
|
|
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH
|
|
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
|
|
cd build
|
|
cmake --build .
|
|
sudo cmake --install .
|
|
df -h
|
|
shell: bash
|
|
|
|
- name: Build nvlink_allocator.so
|
|
run: |
|
|
mkdir -p build/mooncake-transfer-engine/nvlink-allocator
|
|
cd mooncake-transfer-engine/nvlink-allocator
|
|
export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH
|
|
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH
|
|
export LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH
|
|
bash build.sh ../../build/mooncake-transfer-engine/nvlink-allocator/
|
|
shell: bash
|
|
|
|
- name: Run sccache stat for check
|
|
if: ${{ env.SCCACHE_PATH != '' }}
|
|
shell: bash
|
|
run: ${SCCACHE_PATH} --show-stats
|
|
|
|
- name: Generate Python version tag
|
|
id: generate_tag
|
|
run: |
|
|
echo "python_version_tag=$(echo ${{ matrix.python-version }} | tr -d '.')" >> $GITHUB_OUTPUT
|
|
shell: bash
|
|
|
|
- name: Build Python wheel
|
|
run: |
|
|
PYTHON_VERSION=${{ matrix.python-version }} OUTPUT_DIR=dist-py${{ steps.generate_tag.outputs.python_version_tag }} ./scripts/build_wheel.sh
|
|
shell: bash
|
|
|
|
- name: Upload Python wheel artifact
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: mooncake-wheel-cu130-ubuntu-py${{ steps.generate_tag.outputs.python_version_tag }}
|
|
path: mooncake-wheel/dist-py${{ steps.generate_tag.outputs.python_version_tag }}/*.whl
|