Skip to content

Use tokenizer.apply_chat_template() in vLLM #19

Use tokenizer.apply_chat_template() in vLLM

Use tokenizer.apply_chat_template() in vLLM #19

Workflow file for this run

name: Build and Release
on: push
env:
GRPC_VERSION: v1.58.0
permissions:
contents: write
concurrency:
group: ci-releases-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
build-linux:
strategy:
matrix:
include:
- build: 'avx2'
defines: ''
- build: 'avx'
defines: '-DLLAMA_AVX2=OFF'
- build: 'avx512'
defines: '-DLLAMA_AVX512=ON'
- build: 'cuda12'
defines: ''
- build: 'cuda11'
defines: ''
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v4
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg
- name: Install CUDA Dependencies
if: ${{ matrix.build == 'cuda12' || matrix.build == 'cuda11' }}
run: |
if [ "${{ matrix.build }}" == "cuda12" ]; then
export CUDA_VERSION=12-3
else
export CUDA_VERSION=11-7
fi
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update
sudo apt-get install -y cuda-nvcc-${CUDA_VERSION} libcublas-dev-${CUDA_VERSION}
- name: Cache grpc
id: cache-grpc
uses: actions/cache@v3
with:
path: grpc
key: ${{ runner.os }}-grpc-${{ env.GRPC_VERSION }}
- name: Build grpc
if: steps.cache-grpc.outputs.cache-hit != 'true'
run: |
git clone --recurse-submodules -b ${{ env.GRPC_VERSION }} --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-DgRPC_BUILD_TESTS=OFF \
../.. && sudo make --jobs 5 --output-sync=target
- name: Install gRPC
run: |
cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
- name: Build
id: build
env:
CMAKE_ARGS: "${{ matrix.defines }}"
BUILD_ID: "${{ matrix.build }}"
run: |
if [ "${{ matrix.build }}" == "cuda12" ] || [ "${{ matrix.build }}" == "cuda11" ]; then
export BUILD_TYPE=cublas
export PATH=/usr/local/cuda/bin:$PATH
make dist
else
STATIC=true make dist
fi
- uses: actions/upload-artifact@v3
with:
name: ${{ matrix.build }}
path: release/
- name: Release
uses: softprops/action-gh-release@v1
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
build-stablediffusion:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v4
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get install -y --no-install-recommends libopencv-dev
- name: Build stablediffusion
run: |
make backend-assets/grpc/stablediffusion
mkdir -p release && cp backend-assets/grpc/stablediffusion release
- uses: actions/upload-artifact@v3
with:
name: stablediffusion
path: release/
- name: Release
uses: softprops/action-gh-release@v1
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*
build-macOS:
strategy:
matrix:
include:
- build: 'avx2'
defines: ''
- build: 'avx'
defines: '-DLLAMA_AVX2=OFF'
- build: 'avx512'
defines: '-DLLAMA_AVX512=ON'
runs-on: macOS-latest
steps:
- name: Clone
uses: actions/checkout@v4
with:
submodules: true
- uses: actions/setup-go@v4
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
brew install protobuf grpc
- name: Build
id: build
env:
CMAKE_ARGS: "${{ matrix.defines }}"
BUILD_ID: "${{ matrix.build }}"
run: |
export C_INCLUDE_PATH=/usr/local/include
export CPLUS_INCLUDE_PATH=/usr/local/include
make dist
- uses: actions/upload-artifact@v3
with:
name: ${{ matrix.build }}
path: release/
- name: Release
uses: softprops/action-gh-release@v1
if: startsWith(github.ref, 'refs/tags/')
with:
files: |
release/*