llama.cpp/.github/workflows/docker.yml

# This workflow uses actions that are not certified by GitHub.
# They are provided by a third-party and are governed by
# separate terms of service, privacy policy, and support
# documentation.

# GitHub recommends pinning actions to a commit SHA.
# To get a newer version, you will need to update the SHA.
# You can also reference a tag or branch, but the action may change without warning.

name: Publish Docker image

on:
  workflow_dispatch: # allows manual triggering
  schedule:
    # Rebuild daily rather than on every push because it is expensive
    - cron: '12 4 * * *'

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
  cancel-in-progress: true

# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
  packages: write

jobs:
  push_to_registry:
    name: Push Docker image to Docker Hub

    runs-on: ${{ matrix.config.runs_on }}
    env:
      COMMIT_SHA: ${{ github.sha }}
    strategy:
      fail-fast: false
      matrix:
        config:
          # Multi-stage build
          # Note: the arm64 images are failing, which prevents the amd64 images from being built
          # https://github.com/ggml-org/llama.cpp/issues/11888
          #- { tag: "cpu", dockerfile: ".devops/cpu.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, free_disk_space: false }
          - { tag: "cpu",    dockerfile: ".devops/cpu.Dockerfile",    platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false, runs_on: "ubuntu-22.04" }
          - { tag: "cuda cuda12", dockerfile: ".devops/cuda.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true,  runs_on: "ubuntu-22.04", cuda_version: "12.4.0", ubuntu_version: "22.04" }
          - { tag: "cuda13", dockerfile: ".devops/cuda-new.Dockerfile",  platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true,  runs_on: "ubuntu-22.04", cuda_version: "13.1.0", ubuntu_version: "24.04" }
          - { tag: "musa",   dockerfile: ".devops/musa.Dockerfile",   platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true,  runs_on: "ubuntu-22.04" }
          - { tag: "intel",  dockerfile: ".devops/intel.Dockerfile",  platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true,  runs_on: "ubuntu-22.04" }
          - { tag: "vulkan", dockerfile: ".devops/vulkan.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false, runs_on: "ubuntu-22.04" }
          - { tag: "s390x",  dockerfile: ".devops/s390x.Dockerfile",  platforms: "linux/s390x", full: true, light: true, server: true, free_disk_space: false, runs_on: "ubuntu-22.04-s390x" }
          - { tag: "rocm",   dockerfile: ".devops/rocm.Dockerfile",   platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true,  runs_on: "ubuntu-22.04" }
    steps:
      - name: Check out the repo
        uses: actions/checkout@v6
        with:
          fetch-depth: 0 # preserve git history, so we can determine the build number

      - name: Set up QEMU
        if: ${{ matrix.config.tag != 's390x' }}
        uses: docker/setup-qemu-action@v3
        with:
          image: tonistiigi/binfmt:qemu-v7.0.0-28

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

      - name: Log in to Docker Hub
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.repository_owner }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Determine source tag name
        id: srctag
        uses: ./.github/actions/get-tag-name
        env:
          BRANCH_NAME: ${{ github.head_ref || github.ref_name }}

      - name: Determine image tag name
        id: tag
        shell: bash
        run: |
          REPO_OWNER="${GITHUB_REPOSITORY_OWNER@L}"  # to lower case
          REPO_NAME="${{ github.event.repository.name }}"
          PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"

          # list all tags possible
          tags="${{ matrix.config.tag }}"
          for tag in $tags; do
              if [[ "$tag" == "cpu" ]]; then
                  TYPE=""
              else
                  TYPE="-$tag"
              fi
              CACHETAGS="${PREFIX}buildcache${TYPE}"
              FULLTAGS="${FULLTAGS:+$FULLTAGS,}${PREFIX}full${TYPE},${PREFIX}full${TYPE}-${{ steps.srctag.outputs.name }}"
              LIGHTTAGS="${LIGHTTAGS:+$LIGHTTAGS,}${PREFIX}light${TYPE},${PREFIX}light${TYPE}-${{ steps.srctag.outputs.name }}"
              SERVERTAGS="${SERVERTAGS:+$SERVERTAGS,}${PREFIX}server${TYPE},${PREFIX}server${TYPE}-${{ steps.srctag.outputs.name }}"
          done
          echo "cache_output_tags=$CACHETAGS" >> $GITHUB_OUTPUT
          echo "full_output_tags=$FULLTAGS" >> $GITHUB_OUTPUT
          echo "light_output_tags=$LIGHTTAGS" >> $GITHUB_OUTPUT
          echo "server_output_tags=$SERVERTAGS" >> $GITHUB_OUTPUT
          echo "cache_output_tags=$CACHETAGS"  # print out for debugging
          echo "full_output_tags=$FULLTAGS"  # print out for debugging
          echo "light_output_tags=$LIGHTTAGS"  # print out for debugging
          echo "server_output_tags=$SERVERTAGS"  # print out for debugging
        env:
          GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'

      - name: Free Disk Space (Ubuntu)
        if: ${{ matrix.config.free_disk_space == true }}
        uses: ggml-org/free-disk-space@v1.3.1
        with:
          # this might remove tools that are actually needed,
          # if set to "true" but frees about 6 GB
          tool-cache: false

          # all of these default to true, but feel free to set to
          # "false" if necessary for your workflow
          android: true
          dotnet: true
          haskell: true
          large-packages: true
          docker-images: true
          swap-storage: true

      - name: Build and push Full Docker image (tagged + versioned)
        if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.full == true }}
        uses: docker/build-push-action@v6
        with:
          context: .
          push: true
          platforms: ${{ matrix.config.platforms }}
          # tag list is generated from step above
          tags: ${{ steps.tag.outputs.full_output_tags }}
          file: ${{ matrix.config.dockerfile }}
          target: full
          provenance: false
          build-args: |
            ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
            ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
          # using github experimental cache
          #cache-from: type=gha
          #cache-to: type=gha,mode=max
          # return to this if the experimental github cache is having issues
          #cache-to: type=local,dest=/tmp/.buildx-cache
          #cache-from: type=local,src=/tmp/.buildx-cache
          # using registry cache (no storage limit)
          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max

      - name: Build and push Light Docker image (tagged + versioned)
        if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.light == true }}
        uses: docker/build-push-action@v6
        with:
          context: .
          push: true
          platforms: ${{ matrix.config.platforms }}
          # tag list is generated from step above
          tags: ${{ steps.tag.outputs.light_output_tags }}
          file: ${{ matrix.config.dockerfile }}
          target: light
          provenance: false
          build-args: |
            ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
            ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
          # using github experimental cache
          #cache-from: type=gha
          #cache-to: type=gha,mode=max
          # return to this if the experimental github cache is having issues
          #cache-to: type=local,dest=/tmp/.buildx-cache
          #cache-from: type=local,src=/tmp/.buildx-cache
          # using registry cache (no storage limit)
          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max

      - name: Build and push Server Docker image (tagged + versioned)
        if: ${{ (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && matrix.config.server == true }}
        uses: docker/build-push-action@v6
        with:
          context: .
          push: true
          platforms: ${{ matrix.config.platforms }}
          # tag list is generated from step above
          tags: ${{ steps.tag.outputs.server_output_tags }}
          file: ${{ matrix.config.dockerfile }}
          target: server
          provenance: false
          build-args: |
            ${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
            ${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
          # using github experimental cache
          #cache-from: type=gha
          #cache-to: type=gha,mode=max
          # return to this if the experimental github cache is having issues
          #cache-to: type=local,dest=/tmp/.buildx-cache
          #cache-from: type=local,src=/tmp/.buildx-cache
          # using registry cache (no storage limit)
          cache-from: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }}
          cache-to: type=registry,ref=${{ steps.tag.outputs.cache_output_tags }},mode=max

  create_tag:
    name: Create and push git tag
    runs-on: ubuntu-22.04
    permissions:
      contents: write

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Determine source tag name
        id: srctag
        uses: ./.github/actions/get-tag-name
        env:
          BRANCH_NAME: ${{ github.head_ref || github.ref_name }}

      - name: Create and push git tag
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          git tag ${{ steps.srctag.outputs.name }} || exit 0
          git push origin ${{ steps.srctag.outputs.name }} || exit 0