Files
LocalAI/.github/workflows/image-pr.yml
Ettore Di Giacinto bdfa5e934a ci: switch image/backend build cache to a dedicated registry image
- Switch cache-from/cache-to in backend_build.yml and image_build.yml
  from the unused gha cache to type=registry pointing at
  quay.io/go-skynet/ci-cache:cache<tag-suffix>, mode=max with
  ignore-error=true. Master/tag builds populate their own
  per-matrix-entry cache; PR builds read-only.
- Drop the broken generate_grpc_cache.yaml cron. It targeted a `grpc`
  Dockerfile stage that was removed by b1fc5acd in July 2025, has been
  failing every night since, and never populated the gha cache. The new
  registry-cache scheme is self-warming, so no separate populator is
  needed.
- Remove the dead GRPC_VERSION / GRPC_BASE_IMAGE / GRPC_MAKEFLAGS
  build-args from image_build.yml and the orphan ARG GRPC_BASE_IMAGE in
  the root Dockerfile (the root Dockerfile no longer compiles gRPC; the
  source build now lives in backend/Dockerfile.{llama-cpp,
  ik-llama-cpp, turboquant} only and uses its own ARG defaults).
- Drop the unused grpc-base-image input from image_build.yml plus the
  matrix passthroughs in image.yml / image-pr.yml.
- Drop the unused GRPC_VERSION env in test.yml.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7-1m
2026-04-27 13:13:04 +00:00

92 lines
3.5 KiB
YAML

---
name: 'build container images tests'
on:
pull_request:
concurrency:
group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
image-build:
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 }}
secrets:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
# Pushing with all jobs in parallel
# eats the bandwidth of all the nodes
max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
fail-fast: false
matrix:
include:
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-gpu-nvidia-cuda-12'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-gpu-nvidia-cuda-13'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-hipblas'
base-image: "rocm/dev-ubuntu-24.04:7.2.1"
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'sycl'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2025.3.2-0-devel-ubuntu24.04"
tag-suffix: 'sycl'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'vulkan'
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'false'
tag-suffix: '-vulkan-core'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
makeflags: "--jobs=4 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'false'
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'