Merge branch 'matthew/clean' into sync-branch
This commit is contained in:
RandNMR73
@@ -0,0 +1,222 @@
|
||||
name: Publish FastVideo Kernel to PyPI on Version Change
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- "fastvideo-kernel/pyproject.toml"
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
check-version-change:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
version-changed: ${{ steps.check-version.outputs.changed }}
|
||||
new-version: ${{ steps.check-version.outputs.new-version }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 2
|
||||
|
||||
- name: Check if version changed
|
||||
id: check-version
|
||||
run: |
|
||||
cd fastvideo-kernel
|
||||
# Get current commit's version from pyproject.toml
|
||||
# Use ^ to match start of line to avoid matching minimum-version
|
||||
NEW_VERSION=$(grep -oP '^version\s*=\s*"\K[^"]+' pyproject.toml)
|
||||
echo "New version: $NEW_VERSION"
|
||||
|
||||
# Get previous version from git history
|
||||
# Note: git show expects path relative to repo root
|
||||
OLD_VERSION=$(git show HEAD~1:fastvideo-kernel/pyproject.toml | grep -oP '^version\s*=\s*"\K[^"]+' || echo "0.0.0")
|
||||
echo "Old version: $OLD_VERSION"
|
||||
|
||||
if [ "$NEW_VERSION" != "$OLD_VERSION" ]; then
|
||||
echo "Version changed from $OLD_VERSION to $NEW_VERSION"
|
||||
echo "changed=true" >> $GITHUB_OUTPUT
|
||||
echo "new-version=$NEW_VERSION" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "Version did not change"
|
||||
echo "changed=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
build_wheels:
|
||||
name: Build Wheel
|
||||
needs: check-version-change
|
||||
if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [ubuntu-22.04]
|
||||
python-version: ['3.10', '3.11', '3.12']
|
||||
torch-cuda:
|
||||
# - torch-version: '2.5.1'
|
||||
# cuda-version: '12.4.1'
|
||||
# torch-cuda-short: 'cu124'
|
||||
# - torch-version: '2.6.0'
|
||||
# cuda-version: '12.6.3'
|
||||
# torch-cuda-short: 'cu126'
|
||||
# - torch-version: '2.7.1'
|
||||
# cuda-version: '12.8.0'
|
||||
# torch-cuda-short: 'cu128'
|
||||
- torch-version: '2.9.1'
|
||||
cuda-version: '12.8.0'
|
||||
torch-cuda-short: 'cu128'
|
||||
|
||||
steps:
|
||||
- name: Free up disk space
|
||||
run: |
|
||||
echo "Initial disk space:"
|
||||
df -h
|
||||
|
||||
# Remove large directories
|
||||
sudo rm -rf /usr/share/dotnet
|
||||
sudo rm -rf /usr/local/lib/android
|
||||
sudo rm -rf /opt/ghc
|
||||
sudo rm -rf /usr/local/share/boost
|
||||
sudo rm -rf /usr/share/swift
|
||||
sudo rm -rf /usr/local/lib/node_modules
|
||||
sudo rm -rf /usr/local/share/powershell
|
||||
sudo rm -rf /usr/share/rust
|
||||
sudo rm -rf /usr/local/.ghcup
|
||||
|
||||
# Remove cached files
|
||||
sudo rm -rf /var/lib/apt/lists/*
|
||||
sudo rm -rf /var/cache/apt/archives/*
|
||||
|
||||
echo "Disk space after cleanup:"
|
||||
df -h
|
||||
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install CUDA ${{ matrix.torch-cuda.cuda-version }}
|
||||
uses: Jimver/cuda-toolkit@v0.2.21
|
||||
id: cuda-toolkit
|
||||
with:
|
||||
cuda: ${{ matrix.torch-cuda.cuda-version }}
|
||||
linux-local-args: '["--toolkit"]'
|
||||
method: 'network'
|
||||
|
||||
- name: Install dependencies (GCC, Clang, CUDA Paths, Git)
|
||||
run: |
|
||||
sudo apt update
|
||||
sudo apt install -y git patchelf gcc-11 g++-11 clang-11
|
||||
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
|
||||
|
||||
# Allow Git to Access Safe Directory
|
||||
git config --global --add safe.directory /__w/FastVideo/FastVideo
|
||||
|
||||
# Set CUDA environment variables
|
||||
export CUDA_HOME=/usr/local/cuda-${{ matrix.torch-cuda.cuda-version }}
|
||||
export PATH=${CUDA_HOME}/bin:${PATH}
|
||||
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
|
||||
|
||||
# Verify installation
|
||||
gcc --version
|
||||
g++ --version
|
||||
clang-11 --version
|
||||
nvcc --version
|
||||
|
||||
- name: Install PyTorch ${{ matrix.torch-cuda.torch-version }}+cu${{ matrix.torch-cuda.cuda-version }}
|
||||
run: |
|
||||
pip install --upgrade pip
|
||||
pip install typing-extensions==4.12.2
|
||||
pip install --no-cache-dir torch==${{ matrix.torch-cuda.torch-version }} --index-url https://download.pytorch.org/whl/${{matrix.torch-cuda.torch-cuda-short}}
|
||||
nvcc --version
|
||||
python --version
|
||||
python -c "import torch; print('PyTorch:', torch.__version__)"
|
||||
python -c "import torch; print('CUDA:', torch.version.cuda)"
|
||||
python -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"
|
||||
|
||||
- name: Build wheel
|
||||
run: |
|
||||
export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
|
||||
|
||||
pip install setuptools ninja packaging wheel triton scikit-build-core cmake build
|
||||
|
||||
cd fastvideo-kernel
|
||||
git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
|
||||
# Release builds are produced on GPU-less runners, so force-enable TK and target Hopper.
|
||||
export TORCH_CUDA_ARCH_LIST="9.0a"
|
||||
export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
|
||||
|
||||
# Build standard wheel (no local version suffix) for PyPI
|
||||
python -m build --wheel --outdir dist
|
||||
|
||||
# Fix the wheel to be manylinux compliant
|
||||
pip install auditwheel
|
||||
# Point auditwheel at torch libs, but do not vendor them into the wheel.
|
||||
TORCH_LIB_DIR=$(python - <<'PY'
|
||||
import os
|
||||
import torch
|
||||
|
||||
print(os.path.join(os.path.dirname(torch.__file__), "lib"))
|
||||
PY
|
||||
)
|
||||
export LD_LIBRARY_PATH="${TORCH_LIB_DIR}:${LD_LIBRARY_PATH}"
|
||||
# Target manylinux_2_35 (Ubuntu 22.04 native)
|
||||
auditwheel repair dist/*.whl --plat manylinux_2_35_x86_64 -w fixed_dist \
|
||||
--exclude libtorch_cuda.so \
|
||||
--exclude libtorch_cpu.so \
|
||||
--exclude libtorch.so \
|
||||
--exclude libc10.so \
|
||||
--exclude libc10_cuda.so \
|
||||
--exclude libtorch_python.so
|
||||
# Move fixed wheels back to dist for upload consistency
|
||||
rm dist/*.whl
|
||||
mv fixed_dist/*.whl dist/
|
||||
|
||||
- name: Upload wheel artifact
|
||||
# Only upload if it's the "main" CUDA version we want on PyPI
|
||||
# We upload all to artifacts for inspection/GH releases, but give them distinct artifact names
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: fastvideo_kernel-py${{ matrix.python-version }}-${{ matrix.torch-cuda.torch-cuda-short }}-torch${{ matrix.torch-cuda.torch-version }}
|
||||
path: fastvideo-kernel/dist/*.whl
|
||||
retention-days: 90
|
||||
|
||||
publish_package:
|
||||
name: Publish package
|
||||
needs: [build_wheels, check-version-change]
|
||||
if: ${{ needs.check-version-change.outputs.version-changed == 'true' || github.event_name == 'workflow_dispatch' }}
|
||||
runs-on: ubuntu-22.04
|
||||
permissions:
|
||||
id-token: write # Needed for OIDC Trusted Publishing
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.10'
|
||||
|
||||
- name: Download PyPI wheels
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: fastvideo-kernel/dist/
|
||||
pattern: 'fastvideo_kernel-py*'
|
||||
merge-multiple: true
|
||||
|
||||
- name: Build source distribution
|
||||
run: |
|
||||
pip install build scikit-build-core cmake ninja
|
||||
|
||||
cd fastvideo-kernel
|
||||
# We don't need full CUDA/Torch to just package the source (sdist)
|
||||
python -m build --sdist --outdir dist
|
||||
|
||||
- name: Publish release distributions to PyPI
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
packages-dir: fastvideo-kernel/dist/
|
||||
Reference in New Issue
Block a user