mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 13:10:23 -04:00
5a12392570
Yesterday two PRs (#9724 llama.cpp bump, #9731 llama-cpp-darwin consolidation) merged 11 seconds apart. Both shared the same backend.yml concurrency group (ci-backends-refs/heads/master-...) due to "${{ github.head_ref || github.ref }}" — empty head_ref on push events falls through to the static refs/heads/master. With cancel-in-progress: true that meant the second merge cancelled the first's in-flight backend builds. The first PR's CI never finished; the second PR only touched CI files so its run was a no-op. Two changes per workflow: - group: replace "${{ github.head_ref || github.ref }}" with "${{ github.event.pull_request.number || github.sha }}". On PRs this groups by PR number (same as before, just keyed on number not branch name); on push events it groups per-commit, so two master pushes never share a group. - cancel-in-progress: gate on github.event_name == 'pull_request' so rapid pushes to a PR still cancel old runs (newer push wins) but master pushes never cancel each other. Trade-off vs alternatives: - Merge queue would also solve this and additionally test the merged commit before it lands. Heavier process change; out of scope here. - Allowing per-commit master concurrency means two simultaneous master runs may overlap and race on tag pushes, but each commit's manifest digest is unique and the registry is last-writer-wins on tags — newer commit's tag overwrites older. Applied to 11 workflows that share the same concurrency pattern: backend.yml, backend_pr.yml, image.yml, image-pr.yml, lint.yml, test.yml, test-extra.yml, tests-e2e.yml, tests-aio.yml, tests-ui-e2e.yml, generate_intel_image.yaml. Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
103 lines
3.9 KiB
YAML
103 lines
3.9 KiB
YAML
---
|
|
name: 'build container images tests'
|
|
|
|
on:
|
|
pull_request:
|
|
|
|
concurrency:
|
|
group: ci-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
|
|
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
|
|
|
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 }}
|
|
platform-tag: ${{ matrix.platform-tag || '' }}
|
|
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'
|
|
platform-tag: 'amd64'
|
|
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: 'vulkan'
|
|
platforms: 'linux/arm64'
|
|
platform-tag: 'arm64'
|
|
tag-latest: 'false'
|
|
tag-suffix: '-vulkan-core'
|
|
runs-on: 'ubuntu-24.04-arm'
|
|
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'
|
|
|