Skip to content

Update/fix vllm version #31

Update/fix vllm version

Update/fix vllm version #31

name: Build Docker Images
permissions:
contents: read
packages: write
on:
workflow_dispatch:
push:
branches:
- main
paths-ignore:
- 'assets/'
- '**/*.md'
- 'LICENSE'
- '.gitignore'
concurrency:
group: docker-build-${{ github.ref }}
cancel-in-progress: true
jobs:
build:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
include:
- tag: chat
target: chat
cuda_version: "13.0.2"
torch_cuda_arch_list: "8.0 8.6 8.7 8.9 9.0 10.0 12.0 12.1"
vllm_version: "0.19.0"
cuda_toolkit: "cu130"
platforms: linux/amd64,linux/arm64
- tag: serve
target: serve
cuda_version: "13.0.2"
torch_cuda_arch_list: "8.0 8.6 8.7 8.9 9.0 10.0 12.0 12.1"
vllm_version: "0.19.0"
cuda_toolkit: "cu130"
platforms: linux/amd64,linux/arm64
- tag: chat-cu129
target: chat
cuda_version: "12.9.1"
torch_cuda_arch_list: "8.0 8.6 8.7 8.9 9.0 10.0 12.0"
platforms: linux/amd64
- tag: latest
target: optim
cuda_version: "13.0.2"
torch_cuda_arch_list: "8.0 8.6 8.7 8.9 9.0 10.0 12.0 12.1"
platforms: linux/amd64,linux/arm64
- tag: eval
target: eval
cuda_version: "13.0.2"
torch_cuda_arch_list: "8.0 8.6 8.7 8.9 9.0 10.0 12.0 12.1"
platforms: linux/amd64,linux/arm64
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and publish ${{ matrix.tag }} (${{ matrix.platforms }})
uses: docker/build-push-action@v6
with:
context: .
file: docker/Dockerfile
target: ${{ matrix.target }}
push: true
tags: ghcr.io/${{ github.repository }}:${{ matrix.tag }}
platforms: ${{ matrix.platforms }}
build-args: |
CUDA_VERSION=${{ matrix.cuda_version }}
TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}
VLLM_VERSION=${{ matrix.vllm_version }}
CUDA_TOOLKIT=${{ matrix.cuda_toolkit }}
cache-from: type=gha,scope=${{ matrix.tag }}
cache-to: type=gha,mode=max,scope=${{ matrix.tag }}