mirror of
https://github.com/BillyOutlast/flash-attention-prebuild-wheels-rocm.git
synced 2026-07-01 01:27:54 -04:00
Junya Morioka
a7b3fe362e
- Replace WHEEL_NAME variables with WHEEL_PATH to store full file paths instead of just filenames, eliminating redundant directory concatenation - Update all workflow references to use WHEEL_PATH directly in install and upload commands - Simplify manylinux wheel handling by storing full paths in output variables - Reduce tested versions in Linux self-hosted matrix to focus on Python 3.14 - Reduce tested versions in ARM64 self-hosted matrix to focus on Python 3.14 and flash-attn 2.8.3 - Apply formatting standardization to Windows CodeBuild matrix
134 lines
4.6 KiB
YAML
134 lines
4.6 KiB
YAML
# #########################################################
|
|
# Build wheels with GitHub-hosted runner
|
|
# #########################################################
|
|
|
|
name: "[Linux] Build wheels and upload to GitHub Releases"
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
flash-attn-version:
|
|
description: "Flash-Attention version"
|
|
required: true
|
|
type: string
|
|
python-version:
|
|
description: "Python version"
|
|
required: true
|
|
type: string
|
|
torch-version:
|
|
description: "PyTorch version"
|
|
required: true
|
|
type: string
|
|
cuda-version:
|
|
description: "CUDA version"
|
|
required: true
|
|
type: string
|
|
runner:
|
|
description: "Runner type"
|
|
required: false
|
|
type: string
|
|
default: "ubuntu-22.04"
|
|
is-upload:
|
|
description: "Whether to upload the release asset"
|
|
required: false
|
|
type: boolean
|
|
default: true
|
|
|
|
jobs:
|
|
build_wheels:
|
|
name: Build wheels and Upload (Linux x86_64, GitHub hosted runner)
|
|
runs-on: ${{ inputs.runner }}
|
|
env:
|
|
DEBIAN_FRONTEND: noninteractive
|
|
TERM: xterm-256color
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
|
|
- name: Maximize build space
|
|
run: |
|
|
df -h
|
|
echo "-----------------------------"
|
|
sudo rm -rf /usr/share/dotnet
|
|
sudo rm -rf /usr/local/lib/android
|
|
sudo rm -rf /opt/ghc
|
|
sudo rm -rf /opt/hostedtoolcache/CodeQL
|
|
df -h
|
|
|
|
- name: Install build dependencies
|
|
run: |
|
|
sudo apt install -y ninja-build clang time patchelf
|
|
|
|
# Install Python using uv because setup-python needs newer version of glibc
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@v7
|
|
- name: Install Python
|
|
shell: bash
|
|
run: |
|
|
uv venv -p ${{ inputs.python-version }}
|
|
uv pip install -U pip setuptools==75.8.0 wheel packaging psutil auditwheel
|
|
current_dir=$(pwd)
|
|
echo "$current_dir/.venv/bin" >> $GITHUB_PATH
|
|
|
|
- uses: mjun0812/setup-cuda@v1
|
|
with:
|
|
version: ${{ inputs.cuda-version }}
|
|
|
|
- name: Build wheels
|
|
id: build_wheels
|
|
run: |
|
|
chmod +x build_linux.sh
|
|
./build_linux.sh ${{ inputs.flash-attn-version }} ${{ inputs.python-version }} ${{ inputs.torch-version }} ${{ inputs.cuda-version }}
|
|
wheel_path=$(ls flash-attention/dist/*.whl | head -n 1)
|
|
echo "WHEEL_PATH=$wheel_path" >> $GITHUB_OUTPUT
|
|
|
|
- name: Install Test
|
|
run: |
|
|
pip uninstall -y flash-attn > /dev/null 2>&1
|
|
pip install --no-cache-dir ${{ steps.build_wheels.outputs.WHEEL_PATH }}
|
|
python -c "import flash_attn; print(flash_attn.__version__)"
|
|
|
|
- name: Upload Release Asset
|
|
if: ${{ inputs.is-upload }}
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
tag_name=${{ github.ref_name }}
|
|
wheel_path="${{ steps.build_wheels.outputs.WHEEL_PATH }}"
|
|
# Check if the file exists
|
|
if [ ! -f "$wheel_path" ]; then
|
|
echo "Error: Wheel file not found at $wheel_path"
|
|
exit 1
|
|
fi
|
|
# Upload the release asset using GitHub CLI
|
|
gh release upload "$tag_name" "$wheel_path" --clobber
|
|
|
|
- name: Apply auditwheel repair
|
|
continue-on-error: true
|
|
run: |
|
|
auditwheel show ${{ steps.build_wheels.outputs.WHEEL_PATH }}
|
|
auditwheel repair \
|
|
--exclude libc10* --exclude libtorch* --exclude libcu* --exclude libnv* --exclude 'libtorch*' \
|
|
${{ steps.build_wheels.outputs.WHEEL_PATH }} -w flash-attention/dist_manylinux
|
|
wheel_path_manylinux=$(ls flash-attention/dist_manylinux/*manylinux*.whl | head -n 1)
|
|
echo "WHEEL_PATH_MANYLINUX=$wheel_path_manylinux" >> $GITHUB_OUTPUT
|
|
|
|
- name: Test manylinux wheel
|
|
continue-on-error: true
|
|
run: |
|
|
pip uninstall -y flash-attn > /dev/null 2>&1
|
|
pip install --no-cache-dir ${{ steps.build_wheels.outputs.WHEEL_PATH_MANYLINUX }}
|
|
python -c "import flash_attn; print(flash_attn.__version__)"
|
|
|
|
- name: Upload manylinux wheel
|
|
continue-on-error: true
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
wheel_path_manylinux="${{ steps.build_wheels.outputs.WHEEL_PATH_MANYLINUX }}"
|
|
if [ ! -f "$wheel_path_manylinux" ]; then
|
|
echo "Error: Wheel file not found at $wheel_path_manylinux"
|
|
exit 1
|
|
fi
|
|
# Upload the release asset using GitHub CLI
|
|
gh release upload "$tag_name" "$wheel_path_manylinux" --clobber
|