nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[kernel] Reorg and fix fastvideo-kernel (#962)

Browse Source 
Co-authored-by: ShreejithSG <shreejithsg@gmail.com>
This commit is contained in:
William Lin
2025-12-26 01:50:24 -06:00
committed by GitHub
co-authored by ShreejithSG
parent f8bfc76015
commit 2f6230abcf
72 changed files with 1068 additions and 6633 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/fastvideo-kernel-publish.yml
+45 -76
View File
@@ -5,7 +5,7 @@ on:
branches:
- main
paths:
- "csrc/fastvideo_kernel/pyproject.toml"
- "fastvideo-kernel/pyproject.toml"
workflow_dispatch:
jobs:
@@ -23,13 +23,15 @@ jobs:
- name: Check if version changed
id: check-version
run: |
cd csrc/fastvideo_kernel
cd fastvideo-kernel
# Get current commit's version from pyproject.toml
NEW_VERSION=$(grep -oP 'version\s*=\s*"\K[^"]+' pyproject.toml)
# Use ^ to match start of line to avoid matching minimum-version
NEW_VERSION=$(grep -oP '^version\s*=\s*"\K[^"]+' pyproject.toml)
echo "New version: $NEW_VERSION"
# Get previous version from git history
OLD_VERSION=$(git show HEAD~1:./pyproject.toml | grep -oP 'version\s*=\s*"\K[^"]+' || echo "0.0.0")
# 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" != "$OLD_VERSION" ]; then
@@ -51,15 +53,18 @@ jobs:
fail-fast: false
matrix:
os: [ubuntu-22.04]
python-version: ['3.10', '3.11', '3.12', '3.13']
python-version: ['3.10', '3.11', '3.12']
torch-cuda:
- torch-version: '2.5.1'
cuda-version: '12.4.1'
torch-cuda-short: 'cu124'
- torch-version: '2.6.0'
cuda-version: '12.6.3'
torch-cuda-short: 'cu126'
- torch-version: '2.7.1'
# - torch-version: '2.5.1'
# cuda-version: '12.4.1'
# torch-cuda-short: 'cu124'
# - torch-version: '2.6.0'
# cuda-version: '12.6.3'
# torch-cuda-short: 'cu126'
# - torch-version: '2.7.1'
# cuda-version: '12.8.0'
# torch-cuda-short: 'cu128'
- torch-version: '2.9.1'
cuda-version: '12.8.0'
torch-cuda-short: 'cu128'
@@ -138,30 +143,30 @@ jobs:
run: |
export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
pip install setuptools ninja packaging wheel triton
pip install setuptools ninja packaging wheel triton scikit-build-core cmake build
cd csrc/fastvideo_kernel
cd fastvideo-kernel
git submodule update --init --recursive # Ensure ThunderKittens submodule is initialized
python setup.py bdist_wheel --dist-dir=dist
- name: Rename wheel file
run: |
cd csrc/fastvideo_kernel
CUDA_SHORT_VERSION=$(echo ${{ matrix.torch-cuda.cuda-version }} | cut -d. -f1,2 | sed 's/\.//g')
TORCH_SHORT_VERSION=$(echo ${{ matrix.torch-cuda.torch-version }} | cut -d. -f1,2)
# Get the correct version format
tmpname=cu${CUDA_SHORT_VERSION}torch${TORCH_SHORT_VERSION}
wheel_name=$(ls dist/*whl | xargs -n 1 basename | sed "s/-/+$tmpname-/2")
# Rename with version information
ls dist/*whl |xargs -I {} mv {} dist/${wheel_name}
echo "wheel_name=${wheel_name}" >> $GITHUB_ENV
export TORCH_CUDA_ARCH_LIST="9.0a"
# 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
# Target manylinux_2_35 (Ubuntu 22.04 native)
auditwheel repair dist/*.whl --plat manylinux_2_35_x86_64 -w fixed_dist
# 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: ${{ env.wheel_name }}-py${{ matrix.python-version }}
path: csrc/fastvideo_kernel/dist/*.whl
name: fastvideo_kernel-py${{ matrix.python-version }}-${{ matrix.torch-cuda.torch-cuda-short }}-torch${{ matrix.torch-cuda.torch-version }}
path: fastvideo-kernel/dist/*.whl
retention-days: 90
publish_package:
@@ -179,58 +184,22 @@ jobs:
with:
python-version: '3.10'
- name: Install CUDA 12.4.1
uses: Jimver/cuda-toolkit@v0.2.21
id: cuda-toolkit
- name: Download PyPI wheels
uses: actions/download-artifact@v4
with:
cuda: 12.4.1
linux-local-args: '["--toolkit"]'
method: 'network'
sub-packages: '["nvcc"]'
- name: Install dependencies (GCC, Clang, CUDA Paths, Git)
run: |
sudo apt update
sudo apt install -y git patchelf gcc-11 g++-11 clang-11
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
# Allow Git to Access Safe Directory
git config --global --add safe.directory /__w/FastVideo/FastVideo
# Set CUDA environment variables
export CUDA_HOME=/usr/local/cuda-12.4.1
export PATH=${CUDA_HOME}/bin:${PATH}
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:$LD_LIBRARY_PATH
# Verify installation
gcc --version
g++ --version
clang-11 --version
nvcc --version
- name: Install PyTorch 2.5.1+cu12.4.1
run: |
pip install --upgrade pip
pip install typing-extensions==4.12.2
export TORCH_CUDA_VERSION=124
pip install --no-cache-dir torch==2.5.1 --index-url https://download.pytorch.org/whl/cu${TORCH_CUDA_VERSION}
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)"
path: fastvideo-kernel/dist/
pattern: 'fastvideo_kernel-py*'
merge-multiple: true
- name: Build source distribution
run: |
export PYTHONPATH=$GITHUB_WORKSPACE:$PYTHONPATH
pip install build scikit-build-core cmake ninja
pip install setuptools ninja packaging wheel triton
cd csrc/fastvideo_kernel
git submodule update --init --recursive
python setup.py sdist --dist-dir=dist
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: csrc/fastvideo_kernel/dist/
packages-dir: fastvideo-kernel/dist/