llama-swap/.github/workflows/containers.yml

name: Build Containers

on:
  # time has no specific meaning, trying to time it after
  # the llama.cpp daily packages have time to build and publish (~8hr after llama.cpp project's cron)
  # https://github.com/ggml-org/llama.cpp/blob/master/.github/workflows/docker.yml
  schedule:
    - cron: "00 12,18 * * *"

  # Allows manual triggering of the workflow
  workflow_dispatch:
    inputs:
      dryrun:
        description: "Run cleanup step in dry-run mode (log what would be deleted, delete nothing)"
        type: boolean
        default: false

  # Run on workflow file changes (without pushing)
  push:
    paths:
      - '.github/workflows/containers.yml'
      - 'docker/build-container.sh'
      - 'docker/*.Containerfile'

# grant permissions on GITHUB_TOKEN to publish packages
# ref: https://docs.github.com/en/packages/managing-github-packages-using-github-actions-workflows/publishing-and-installing-a-package-with-github-actions#publishing-a-package-using-an-action
permissions:
  contents: read
  packages: write
  id-token: write

jobs:
  build-and-push:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        platform: [intel, cuda, cuda13, vulkan, cpu, musa, rocm]
      fail-fast: false
    steps:
      - name: Checkout code
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # 6.0.2

      - name: Free up disk space
        if: matrix.platform == 'rocm'
        run: |
          echo "Before cleanup:"
          df -h
          sudo rm -rf /usr/share/dotnet
          sudo rm -rf /usr/local/lib/android
          sudo rm -rf /opt/ghc
          sudo rm -rf /opt/hostedtoolcache/CodeQL
          sudo docker system prune -af
          echo "After cleanup:"
          df -h

      # QEMU enables arm64 cross-builds on the amd64 GitHub runner.
      # Currently only the cpu backend goes multi-arch; the action is a
      # no-op for amd64-only builds, so leaving it on for every matrix
      # entry keeps the workflow simple.
      - name: Set up QEMU
        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a #v4.0.0

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd #v4.0.0

      - name: Log in to GitHub Container Registry
        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 #v4.1.0
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Run build-container
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: ./docker/build-container.sh ${{ matrix.platform }} ${{ github.event_name != 'push' }}

  # actions/delete-package-versions can't see manifest lists: pushing
  # a multi-arch image with `docker buildx --push` creates a tagged OCI
  # index plus one untagged per-platform manifest per arch, and
  # `delete-only-untagged-versions: true` then nukes the per-platform
  # children, leaving the index dangling — `docker pull :cpu` 404s on
  # the referenced digest. dataaxiom/ghcr-cleanup-action walks tagged
  # manifest lists and excludes their children from deletion.
  delete-untagged-containers:
    needs: build-and-push
    # Skip on forks — the delete API requires package-admin on the
    # upstream account and would otherwise red-x every fork CI run.
    if: github.repository == 'mostlygeek/llama-swap'
    runs-on: ubuntu-latest
    steps:
      - uses: dataaxiom/ghcr-cleanup-action@cd0cdb900b5dbf3a6f2cc869f0dbb0b8211f50c4 # v1.0.16
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          package: llama-swap
          delete-untagged: true
          dry-run: ${{ inputs.dryrun || false }}