llama.cpp/.github/workflows/build-docker.yaml

name: Build Docker

on: workflow_dispatch

permissions:
  contents: write
  packages: write

jobs:
  docker:
    name: Build and push Docker image
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v3
        with:
          submodules: "true"

      - name: Set up QEMU
        uses: docker/setup-qemu-action@v2

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v2

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2 
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Build and push
        uses: docker/build-push-action@v4
        with:
          context: .
          push: true # push to registry
          pull: true # always fetch the latest base images
          platforms: linux/amd64,linux/arm64 # build for both amd64 and arm64
          tags: ghcr.io/abetlen/llama-cpp-python:latest

  docker-cuda:
    name: Build and push Docker CUDA image
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v3
        with:
          submodules: "true"

      - name: Setup CUDA 12.1
        uses: Jimver/cuda-toolkit@v0.2.10
        id: cuda-toolkit
        with:
          cuda: '12.1.0'
          method: network

      - name: Set up QEMU
        uses: docker/setup-qemu-action@v2

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v2

      - name: Login to GitHub Container Registry
        uses: docker/login-action@v2 
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Build and push
        uses: docker/build-push-action@v4
        with:
          file: Dockerfile.cuda
          context: .
          push: true # push to registry
          pull: true # always fetch the latest base images
          platforms: linux/amd64,linux/arm64 # build for both amd64 and arm64
          tags: ghcr.io/abetlen/llama-cpp-python-cuda:latest