Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: add precompile kernels workflow #1971

Closed
wants to merge 2 commits into from
Closed

feat: add precompile kernels workflow #1971

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
58ac1d7
feat: add basic workflow
drbh May 29, 2024
129f0ed
fix: adjust whl names and upload all
drbh May 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
188 changes: 188 additions & 0 deletions .github/workflows/precompile-kernels.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,188 @@
# based on https://github.com/Dao-AILab/flash-attention/blob/main/.github/workflows/publish.yml
name: Build wheels

on:
workflow_dispatch:
push:
branches:
- main
pull_request:

jobs:
build_wheels:
name: Build Wheel
runs-on: ${{ matrix.os }}

strategy:
fail-fast: false
matrix:
# Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
# manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
os: [ubuntu-20.04]
python-version: [
# "3.7", "3.8", "3.9", "3.10",
"3.11",
]
torch-version: [
# "1.12.1", "1.13.1", "2.0.1", "2.1.2", "2.2.2",
"2.3.0",
]
cuda-version: [
# "11.8.0",
"12.2.2",
]
# We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
# Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.
# Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs)
# when building without C++11 ABI and using it on nvcr images.
cxx11_abi: [
# "FALSE",
"TRUE",
]
exclude:
# see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
# Pytorch <= 1.12 does not support Python 3.11
- torch-version: "1.12.1"
python-version: "3.11"
# Pytorch >= 2.0 only supports Python >= 3.8
- torch-version: "2.0.1"
python-version: "3.7"
- torch-version: "2.1.2"
python-version: "3.7"
- torch-version: "2.2.2"
python-version: "3.7"
- torch-version: "2.3.0"
python-version: "3.7"
# Pytorch <= 2.0 only supports CUDA <= 11.8
- torch-version: "1.12.1"
cuda-version: "12.2.2"
- torch-version: "1.13.1"
cuda-version: "12.2.2"
- torch-version: "2.0.1"
cuda-version: "12.2.2"

steps:
- name: Checkout
uses: actions/checkout@v3

- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}

- name: Set CUDA and PyTorch versions
run: |
echo "MATRIX_CUDA_VERSION=$(echo ${{ matrix.cuda-version }} | awk -F \. {'print $1 $2'})" >> $GITHUB_ENV
echo "MATRIX_TORCH_VERSION=$(echo ${{ matrix.torch-version }} | awk -F \. {'print $1 "." $2'})" >> $GITHUB_ENV
echo "MATRIX_PYTHON_VERSION=$(echo ${{ matrix.python-version }} | awk -F \. {'print $1 $2'})" >> $GITHUB_ENV

- name: Free up disk space
if: ${{ runner.os == 'Linux' }}
# https://github.com/easimon/maximize-build-space/blob/master/action.yml
# https://github.com/easimon/maximize-build-space/tree/test-report
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL

- name: Set up swap space
if: runner.os == 'Linux'
uses: pierotofy/set-swap-space@v1.0
with:
swap-size-gb: 10

- name: Install CUDA ${{ matrix.cuda-version }}
if: ${{ matrix.cuda-version != 'cpu' }}
uses: Jimver/cuda-toolkit@v0.2.14
id: cuda-toolkit
with:
cuda: ${{ matrix.cuda-version }}
linux-local-args: '["--toolkit"]'
# default method is "local", and we're hitting some error with caching for CUDA 11.8 and 12.1
# method: ${{ (matrix.cuda-version == '11.8.0' || matrix.cuda-version == '12.1.0') && 'network' || 'local' }}
method: "network"
# We need the cuda libraries (e.g. cuSparse, cuSolver) for compiling PyTorch extensions,
# not just nvcc
# sub-packages: '["nvcc"]'

- name: Install PyTorch ${{ matrix.torch-version }}+cu${{ matrix.cuda-version }}
run: |
pip install --upgrade pip
# If we don't install before installing Pytorch, we get error for torch 2.0.1
# ERROR: Could not find a version that satisfies the requirement setuptools>=40.8.0 (from versions: none)
pip install lit
# We want to figure out the CUDA version to download pytorch
# e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
# see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
# This code is ugly, maybe there's a better way to do this.
export TORCH_CUDA_VERSION=$(python -c "from os import environ as env; \
minv = {'1.12': 113, '1.13': 116, '2.0': 117, '2.1': 118, '2.2': 118, '2.3': 118}[env['MATRIX_TORCH_VERSION']]; \
maxv = {'1.12': 116, '1.13': 117, '2.0': 118, '2.1': 121, '2.2': 121, '2.3': 121}[env['MATRIX_TORCH_VERSION']]; \
print(max(min(int(env['MATRIX_CUDA_VERSION']), maxv), minv))" \
)
if [[ ${{ matrix.torch-version }} == *"dev"* ]]; then
if [[ ${MATRIX_TORCH_VERSION} == "2.2" ]]; then
# --no-deps because we can't install old versions of pytorch-triton
pip install typing-extensions jinja2
pip install --no-cache-dir --no-deps --pre https://download.pytorch.org/whl/nightly/cu${TORCH_CUDA_VERSION}/torch-${{ matrix.torch-version }}%2Bcu${TORCH_CUDA_VERSION}-cp${MATRIX_PYTHON_VERSION}-cp${MATRIX_PYTHON_VERSION}-linux_x86_64.whl
else
pip install --no-cache-dir --pre torch==${{ matrix.torch-version }} --index-url https://download.pytorch.org/whl/nightly/cu${TORCH_CUDA_VERSION}
fi
else
pip install --no-cache-dir torch==${{ matrix.torch-version }} --index-url https://download.pytorch.org/whl/cu${TORCH_CUDA_VERSION}
fi
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)"
shell: bash

- name: Build wheel
run: |
# Ensure we have the correct version of setuptools to avoid compatibility issues with CUDA
pip install setuptools==68.0.0
pip install ninja packaging wheel
# Set up the environment for CUDA
export PATH=/usr/local/nvidia/bin:/usr/local/nvidia/lib64:$PATH
export LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:$LD_LIBRARY_PATH
# Clone the repository at the specific commit
git clone https://github.com/HazyResearch/flash-attention.git
cd flash-attention
git checkout 3a9bfd076f98746c73362328958dbc68d145fbec
# Build the wheel with limited jobs to prevent OOM issues on the GitHub runner
MAX_JOBS=2 FLASH_ATTENTION_FORCE_BUILD="TRUE" FLASH_ATTENTION_FORCE_CXX11_ABI=${{ matrix.cxx11_abi }} python setup.py bdist_wheel --dist-dir=../dist
# Build kernels inside the repository
cd csrc/rotary
MAX_JOBS=2 python setup.py bdist_wheel --dist-dir=../../../dist
cd ../layer_norm
MAX_JOBS=2 python setup.py bdist_wheel --dist-dir=../../../dist
# build the kernels for vllm as well
cd ../..
git clone https://github.com/Narsil/vllm.git
cd vllm
git checkout b5dfc61db88a81069e45b44f7cc99bd9e62a60fa
export TORCH_CUDA_ARCH_LIST="8.0 8.6 8.9 9.0"
python setup.py bdist_wheel --dist-dir=../dist
# Generate a custom name for the wheel to include CUDA and Torch versions
cd ../dist
tmpname=cu${MATRIX_CUDA_VERSION}torch${MATRIX_TORCH_VERSION}cxx11abi${{ matrix.cxx11_abi }}
for wheel in *.whl; do
new_wheel_name=$(echo "$wheel" | sed "s/-/+$tmpname-/2")
mv "$wheel" "$new_wheel_name"
done
# Save the wheel name to the GitHub environment
echo "wheel_name=$(ls *+$tmpname-*.whl)" >> $GITHUB_ENV

- name: Log Built Wheels
run: |
ls dist

- name: Install Hugging Face CLI
run: |
pip install huggingface_hub

- name: Upload to Hugging Face Hub
run: |
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_PRECOMPILE_TOKEN }}
huggingface-cli upload drbh/flash-attention-pre-compile dist/*
Loading