LocalAI/.github/workflows/image.yml

---
name: 'build container images'

on:
  push:
    branches:
      - master
    tags:
      - '*'

concurrency:
  group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
  cancel-in-progress: true

jobs:
  hipblas-jobs:
    uses: ./.github/workflows/image_build.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
      tag-suffix: ${{ matrix.tag-suffix }}
      ffmpeg: ${{ matrix.ffmpeg }}
      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 }}
      grpc-base-image: ${{ matrix.grpc-base-image }}
      aio: ${{ matrix.aio }}
      makeflags: ${{ matrix.makeflags }}
      latest-image: ${{ matrix.latest-image }}
      latest-image-aio: ${{ matrix.latest-image-aio }}
    secrets:
      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
    strategy:
      max-parallel: 2
      matrix:
        include:
          - build-type: 'hipblas'
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-hipblas'
            ffmpeg: 'true'
            base-image: "rocm/dev-ubuntu-22.04:6.1"
            grpc-base-image: "ubuntu:22.04"
            runs-on: 'arc-runner-set'
            makeflags: "--jobs=3 --output-sync=target"
            latest-image: 'latest-gpu-hipblas'
            aio: "-aio-gpu-hipblas"
            latest-image-aio: 'latest-aio-gpu-hipblas'

  core-image-build:
    uses: ./.github/workflows/image_build.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
      tag-suffix: ${{ matrix.tag-suffix }}
      ffmpeg: ${{ matrix.ffmpeg }}
      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 }}
      aio: ${{ matrix.aio }}
      base-image: ${{ matrix.base-image }}
      grpc-base-image: ${{ matrix.grpc-base-image }}
      makeflags: ${{ matrix.makeflags }}
      latest-image: ${{ matrix.latest-image }}
      latest-image-aio: ${{ matrix.latest-image-aio }}
      skip-drivers: ${{ matrix.skip-drivers }}
    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,linux/arm64'
            tag-latest: 'auto'
            tag-suffix: ''
            ffmpeg: 'true'
            base-image: "ubuntu:22.04"
            runs-on: 'arc-runner-set'
            aio: "-aio-cpu"
            latest-image: 'latest-cpu'
            latest-image-aio: 'latest-aio-cpu'
            makeflags: "--jobs=4 --output-sync=target"
            skip-drivers: 'false'
          - build-type: 'cublas'
            cuda-major-version: "11"
            cuda-minor-version: "7"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda11'
            ffmpeg: 'true'
            runs-on: 'arc-runner-set'
            base-image: "ubuntu:22.04"
            makeflags: "--jobs=4 --output-sync=target"
            skip-drivers: 'false'
            latest-image: 'latest-gpu-nvidia-cuda-11'
            aio: "-aio-gpu-nvidia-cuda-11"
            latest-image-aio: 'latest-aio-gpu-nvidia-cuda-11'
          - build-type: 'cublas'
            cuda-major-version: "12"
            cuda-minor-version: "0"
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-cublas-cuda12'
            ffmpeg: 'true'
            runs-on: 'arc-runner-set'
            base-image: "ubuntu:22.04"
            skip-drivers: 'false'
            makeflags: "--jobs=4 --output-sync=target"
            latest-image: 'latest-gpu-nvidia-cuda-12'
            aio: "-aio-gpu-nvidia-cuda-12"
            latest-image-aio: 'latest-aio-gpu-nvidia-cuda-12'
          - build-type: 'vulkan'
            platforms: 'linux/amd64'
            tag-latest: 'false'
            tag-suffix: '-vulkan'
            ffmpeg: 'true'
            runs-on: 'arc-runner-set'
            base-image: "ubuntu:22.04"
            skip-drivers: 'false'
            makeflags: "--jobs=4 --output-sync=target"
            latest-image: 'latest-gpu-vulkan'
            aio: "-aio-gpu-vulkan"
            latest-image-aio: 'latest-aio-gpu-vulkan'
          - build-type: 'sycl_f16'
            platforms: 'linux/amd64'
            tag-latest: 'false'
            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
            grpc-base-image: "ubuntu:22.04"
            tag-suffix: '-sycl-f16'
            ffmpeg: 'true'
            runs-on: 'arc-runner-set'
            makeflags: "--jobs=3 --output-sync=target"
            latest-image: 'latest-gpu-intel-f16'
            aio: "-aio-gpu-intel-f16"
            latest-image-aio: 'latest-aio-gpu-intel-f16'
          - build-type: 'sycl_f32'
            platforms: 'linux/amd64'
            tag-latest: 'false'
            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
            grpc-base-image: "ubuntu:22.04"
            tag-suffix: '-sycl-f32'
            ffmpeg: 'true'
            runs-on: 'arc-runner-set'
            makeflags: "--jobs=3 --output-sync=target"
            latest-image: 'latest-gpu-intel-f32'
            aio: "-aio-gpu-intel-f32"
            latest-image-aio: 'latest-aio-gpu-intel-f32'

  gh-runner:
    uses: ./.github/workflows/image_build.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
      tag-suffix: ${{ matrix.tag-suffix }}
      ffmpeg: ${{ matrix.ffmpeg }}
      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 }}
      aio: ${{ matrix.aio }}
      base-image: ${{ matrix.base-image }}
      grpc-base-image: ${{ matrix.grpc-base-image }}
      makeflags: ${{ matrix.makeflags }}
      latest-image: ${{ matrix.latest-image }}
      latest-image-aio: ${{ matrix.latest-image-aio }}
      skip-drivers: ${{ matrix.skip-drivers }}
    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: 'false'
            tag-suffix: '-nvidia-l4t-arm64'
            latest-image: 'latest-nvidia-l4t-arm64'
            ffmpeg: 'true'
            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'