LocalAI/.github/workflows/base-images.yml

---
name: 'build base-grpc images'

# Builds + pushes pre-compiled builder base images that downstream
# llama-cpp / ik-llama-cpp / turboquant variant Dockerfiles will FROM
# (PR 2). Each base contains apt deps + protoc + cmake + gRPC at
# /opt/grpc + (conditionally) CUDA / ROCm / Vulkan toolchains.
#
# Triggers:
#   - schedule (Saturdays 05:00 UTC) - picks up Ubuntu/CUDA/ROCm
#     security updates and re-runs ahead of the backend.yml weekly
#     cron (Sundays 06:00 UTC).
#   - workflow_dispatch - manual one-off rebuild.
#   - push to master that touches Dockerfile.base-grpc-builder or
#     this workflow itself - keeps bases in sync with their inputs.
#
# Bootstrap (one-time after this PR merges):
#   gh workflow run base-images.yml --ref master
# Wait ~30 min for all 9 matrix variants to push to
# quay.io/go-skynet/ci-cache:base-grpc-* before merging PR 2.

on:
  schedule:
    - cron: '0 5 * * 6'
  workflow_dispatch:
  push:
    branches: [master]
    paths:
      - 'backend/Dockerfile.base-grpc-builder'
      - '.github/workflows/base-images.yml'
      # The install logic and apt-mirror helper are bind-mounted into
      # Dockerfile.base-grpc-builder at build time — changes to either
      # affect the produced base images and must trigger a rebuild.
      - '.docker/install-base-deps.sh'
      - '.docker/apt-mirror.sh'

concurrency:
  group: ci-base-images-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

jobs:
  build:
    if: github.repository == 'mudler/LocalAI'
    runs-on: ${{ matrix.runs-on }}
    strategy:
      fail-fast: false
      matrix:
        include:
          - tag: 'base-grpc-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'ubuntu:24.04'
            build-type: ''
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          - tag: 'base-grpc-arm64'
            runs-on: 'ubuntu-24.04-arm'
            base-image: 'ubuntu:24.04'
            build-type: ''
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          - tag: 'base-grpc-cuda-12-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'ubuntu:24.04'
            build-type: 'cublas'
            cuda-major-version: '12'
            cuda-minor-version: '8'
            ubuntu-version: '2404'
          - tag: 'base-grpc-cuda-13-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'ubuntu:22.04'
            build-type: 'cublas'
            cuda-major-version: '13'
            cuda-minor-version: '0'
            ubuntu-version: '2204'
          - tag: 'base-grpc-cuda-13-arm64'
            runs-on: 'ubuntu-24.04-arm'
            base-image: 'ubuntu:24.04'
            build-type: 'cublas'
            cuda-major-version: '13'
            cuda-minor-version: '0'
            ubuntu-version: '2404'
          - tag: 'base-grpc-rocm-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'rocm/dev-ubuntu-24.04:7.2.1'
            build-type: 'hipblas'
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          - tag: 'base-grpc-vulkan-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'ubuntu:24.04'
            build-type: 'vulkan'
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          - tag: 'base-grpc-vulkan-arm64'
            runs-on: 'ubuntu-24.04-arm'
            base-image: 'ubuntu:24.04'
            build-type: 'vulkan'
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          - tag: 'base-grpc-intel-amd64'
            runs-on: 'ubuntu-latest'
            base-image: 'intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04'
            build-type: 'sycl'
            cuda-major-version: ''
            cuda-minor-version: ''
            ubuntu-version: '2404'
          # Legacy JetPack r36.4.0 base for older Jetson devices (CUDA 12).
          # Distinct from base-grpc-cuda-13-arm64 (Ubuntu 24.04 + CUDA 13 sbsa)
          # which targets newer Jetsons. Some matrix entries
          # (-nvidia-l4t-arm64-llama-cpp / -turboquant) still build against
          # the JetPack image, so we need a matching base.
          - tag: 'base-grpc-l4t-cuda-12-arm64'
            runs-on: 'ubuntu-24.04-arm'
            base-image: 'nvcr.io/nvidia/l4t-jetpack:r36.4.0'
            build-type: 'l4t'
            cuda-major-version: '12'
            cuda-minor-version: '0'
            ubuntu-version: '2204'
            # JetPack r36.4.0 already ships CUDA preinstalled at /usr/local/cuda;
            # apt-installing cuda-nvcc-12-0 from the public repos fails because
            # those packages aren't published for the JetPack apt feed. Match
            # the original l4t matrix entry which set skip-drivers: 'true'.
            skip-drivers: 'true'
    steps:
      - uses: actions/checkout@v6
        with:
          submodules: false
      - name: Free disk space
        uses: ./.github/actions/free-disk-space
      - name: Set up build disk
        uses: ./.github/actions/setup-build-disk
      - uses: docker/setup-qemu-action@master
        with:
          platforms: all
      - uses: docker/setup-buildx-action@master
      - uses: docker/login-action@v4
        with:
          registry: quay.io
          username: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
          password: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
      - uses: docker/build-push-action@v7
        with:
          context: .
          file: ./backend/Dockerfile.base-grpc-builder
          build-args: |
            BASE_IMAGE=${{ matrix.base-image }}
            BUILD_TYPE=${{ matrix.build-type }}
            CUDA_MAJOR_VERSION=${{ matrix.cuda-major-version }}
            CUDA_MINOR_VERSION=${{ matrix.cuda-minor-version }}
            UBUNTU_VERSION=${{ matrix.ubuntu-version }}
            SKIP_DRIVERS=${{ matrix.skip-drivers || 'false' }}
          cache-from: type=registry,ref=quay.io/go-skynet/ci-cache:cache-${{ matrix.tag }}
          cache-to: type=registry,ref=quay.io/go-skynet/ci-cache:cache-${{ matrix.tag }},mode=max,ignore-error=true
          provenance: false
          tags: quay.io/go-skynet/ci-cache:${{ matrix.tag }}
          push: true