---
  name: 'build container images'
  
  on:
    push:
      branches:
        - master
      tags:
        - '*'
  
  concurrency:
    group: ci-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
    cancel-in-progress: ${{ github.event_name == 'pull_request' }}
  
  jobs:
    hipblas-jobs:
      if: github.repository == 'mudler/LocalAI'
      uses: ./.github/workflows/image_build.yml
      with:
        tag-latest: ${{ matrix.tag-latest }}
        tag-suffix: ${{ matrix.tag-suffix }}
        build-type: ${{ matrix.build-type }}
        cuda-major-version: ${{ matrix.cuda-major-version }}
        cuda-minor-version: ${{ matrix.cuda-minor-version }}
        platforms: ${{ matrix.platforms }}
        runs-on: ${{ matrix.runs-on }}
        base-image: ${{ matrix.base-image }}
        makeflags: ${{ matrix.makeflags }}
        ubuntu-version: ${{ matrix.ubuntu-version }}
        ubuntu-codename: ${{ matrix.ubuntu-codename }}
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
      strategy:
        matrix:
          include:
            - build-type: 'hipblas'
              platforms: 'linux/amd64'
              tag-latest: 'auto'
              tag-suffix: '-gpu-hipblas'
              base-image: "rocm/dev-ubuntu-24.04:7.2.1"
              runs-on: 'ubuntu-latest'
              makeflags: "--jobs=3 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'

    core-image-build:
      if: github.repository == 'mudler/LocalAI'
      uses: ./.github/workflows/image_build.yml
      with:
        tag-latest: ${{ matrix.tag-latest }}
        tag-suffix: ${{ matrix.tag-suffix }}
        build-type: ${{ matrix.build-type }}
        cuda-major-version: ${{ matrix.cuda-major-version }}
        cuda-minor-version: ${{ matrix.cuda-minor-version }}
        platforms: ${{ matrix.platforms }}
        platform-tag: ${{ matrix.platform-tag || '' }}
        runs-on: ${{ matrix.runs-on }}
        base-image: ${{ matrix.base-image }}
        makeflags: ${{ matrix.makeflags }}
        skip-drivers: ${{ matrix.skip-drivers }}
        ubuntu-version: ${{ matrix.ubuntu-version }}
        ubuntu-codename: ${{ matrix.ubuntu-codename }}
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
      strategy:
        #max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
        matrix:
          include:
            - build-type: ''
              platforms: 'linux/amd64'
              platform-tag: 'amd64'
              tag-latest: 'auto'
              tag-suffix: ''
              base-image: "ubuntu:24.04"
              runs-on: 'ubuntu-latest'
              makeflags: "--jobs=4 --output-sync=target"
              skip-drivers: 'false'
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: ''
              platforms: 'linux/arm64'
              platform-tag: 'arm64'
              tag-latest: 'auto'
              tag-suffix: ''
              base-image: "ubuntu:24.04"
              runs-on: 'ubuntu-24.04-arm'
              makeflags: "--jobs=4 --output-sync=target"
              skip-drivers: 'false'
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: 'cublas'
              cuda-major-version: "12"
              cuda-minor-version: "8"
              platforms: 'linux/amd64'
              tag-latest: 'auto'
              tag-suffix: '-gpu-nvidia-cuda-12'
              runs-on: 'ubuntu-latest'
              base-image: "ubuntu:24.04"
              skip-drivers: 'false'
              makeflags: "--jobs=4 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: 'cublas'
              cuda-major-version: "13"
              cuda-minor-version: "0"
              platforms: 'linux/amd64'
              tag-latest: 'auto'
              tag-suffix: '-gpu-nvidia-cuda-13'
              runs-on: 'ubuntu-latest'
              base-image: "ubuntu:22.04"
              skip-drivers: 'false'
              makeflags: "--jobs=4 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: 'vulkan'
              platforms: 'linux/amd64'
              platform-tag: 'amd64'
              tag-latest: 'auto'
              tag-suffix: '-gpu-vulkan'
              runs-on: 'ubuntu-latest'
              base-image: "ubuntu:24.04"
              skip-drivers: 'false'
              makeflags: "--jobs=4 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: 'vulkan'
              platforms: 'linux/arm64'
              platform-tag: 'arm64'
              tag-latest: 'auto'
              tag-suffix: '-gpu-vulkan'
              runs-on: 'ubuntu-24.04-arm'
              base-image: "ubuntu:24.04"
              skip-drivers: 'false'
              makeflags: "--jobs=4 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'
            - build-type: 'intel'
              platforms: 'linux/amd64'
              tag-latest: 'auto'
              base-image: "intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04"
              tag-suffix: '-gpu-intel'
              runs-on: 'ubuntu-latest'
              makeflags: "--jobs=3 --output-sync=target"
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'

    core-image-merge:
      # !cancelled(): without it, GHA's default `needs:` cascade skips the
      # merge whenever any matrix cell of the parent build fails or is
      # cancelled. Same fix as backend.yml's merge jobs — we still want to
      # publish the manifest list for tag-suffixes whose legs all succeeded.
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: core-image-build
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: ''
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    gpu-vulkan-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: core-image-build
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-gpu-vulkan'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    # Single-arch server-image merges. Same conceptual fix as the backend
    # singletons in PR #9781: image_build.yml pushes by canonical digest
    # only, so without a downstream merge step there's no tag for consumers
    # (no :latest-gpu-nvidia-cuda-12, no :v<X>-gpu-nvidia-cuda-12, etc.).
    # Each merge job needs only its parent build matrix and is filtered by
    # tag-suffix in image_merge.yml's artifact-download pattern.
    gpu-nvidia-cuda-12-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: core-image-build
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-gpu-nvidia-cuda-12'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    gpu-nvidia-cuda-13-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: core-image-build
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-gpu-nvidia-cuda-13'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    gpu-intel-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: core-image-build
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-gpu-intel'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    gpu-hipblas-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: hipblas-jobs
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-gpu-hipblas'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    nvidia-l4t-arm64-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: gh-runner
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-nvidia-l4t-arm64'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    nvidia-l4t-arm64-cuda-13-image-merge:
      if: ${{ !cancelled() && github.repository == 'mudler/LocalAI' }}
      needs: gh-runner
      uses: ./.github/workflows/image_merge.yml
      with:
        tag-latest: 'auto'
        tag-suffix: '-nvidia-l4t-arm64-cuda-13'
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}

    gh-runner:
      if: github.repository == 'mudler/LocalAI'
      uses: ./.github/workflows/image_build.yml
      with:
        tag-latest: ${{ matrix.tag-latest }}
        tag-suffix: ${{ matrix.tag-suffix }}
        build-type: ${{ matrix.build-type }}
        cuda-major-version: ${{ matrix.cuda-major-version }}
        cuda-minor-version: ${{ matrix.cuda-minor-version }}
        platforms: ${{ matrix.platforms }}
        runs-on: ${{ matrix.runs-on }}
        base-image: ${{ matrix.base-image }}
        makeflags: ${{ matrix.makeflags }}
        skip-drivers: ${{ matrix.skip-drivers }}
        ubuntu-version: ${{ matrix.ubuntu-version }}
        ubuntu-codename: ${{ matrix.ubuntu-codename }}
      secrets:
        dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
        dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
        quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
        quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
      strategy:
        matrix:
          include:
            - build-type: 'cublas'
              cuda-major-version: "12"
              cuda-minor-version: "0"
              platforms: 'linux/arm64'
              tag-latest: 'auto'
              tag-suffix: '-nvidia-l4t-arm64'
              base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
              runs-on: 'ubuntu-24.04-arm'
              makeflags: "--jobs=4 --output-sync=target"
              skip-drivers: 'true'
              ubuntu-version: "2204"
              ubuntu-codename: 'jammy'
            - build-type: 'cublas'
              cuda-major-version: "13"
              cuda-minor-version: "0"
              platforms: 'linux/arm64'
              tag-latest: 'auto'
              tag-suffix: '-nvidia-l4t-arm64-cuda-13'
              base-image: "ubuntu:24.04"
              runs-on: 'ubuntu-24.04-arm'
              makeflags: "--jobs=4 --output-sync=target"
              skip-drivers: 'false'
              ubuntu-version: '2404'
              ubuntu-codename: 'noble'