mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
35f6db8c76
Symptom (run 25612992409): backend-merge-jobs failed with
"quay.io/go-skynet/local-ai-backends@sha256:fdbd93ca...: not found"
even though the per-arch build for -cpu-llama-cpp pushed that exact
digest 14h31m earlier.
Root cause: backend-merge-jobs was gated on the WHOLE backend-jobs
matrix (`needs: backend-jobs`). The multi-arch -cpu-llama-cpp legs
finished within 30 min, but a single-arch CUDA-12-llama-cpp slot in
the same matrix queued for ~8h (max-parallel: 8 throttle) and then
took ~6h to build cold. By the time it freed the merge to run, quay's
GC had reaped the per-arch digests pushed by the fast multi-arch legs
the day before.
Fix: split the linux backend matrix in two.
backend-jobs-multiarch - entries with `platform-tag` set (paired
per-arch legs that feed backend-merge-jobs).
backend-jobs-singlearch - entries without `platform-tag` (heavy
standalone builds: CUDA, ROCm, Intel oneAPI, vLLM, sglang, etc.).
backend-merge-jobs now `needs:` only backend-jobs-multiarch. The
multi-arch matrix completes in ~2-3h, well inside quay's GC window.
Heavy single-arch entries keep running independently with no merge
dependency.
scripts/changed-backends.js gains a splitByArch() helper that
partitions filtered entries by whether `platform-tag` is set, and
emits matrix-singlearch + matrix-multiarch + has-backends-singlearch
+ has-backends-multiarch outputs (replacing the previous combined
matrix / has-backends pair). Applied in both the full-matrix and
filtered-matrix code paths. Smoke test: 199 single-arch + 72 multi-
arch + 35 darwin = 271 total entries; 36 merge-matrix entries
(one per multi-arch backend pair). Matches expectation.
Local `make backends/<name>` is unaffected — the script's outputs
only feed CI workflow matrices.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
134 lines
5.6 KiB
YAML
134 lines
5.6 KiB
YAML
name: 'build backend container images (PR-filtered)'
|
|
|
|
on:
|
|
pull_request:
|
|
|
|
concurrency:
|
|
group: ci-backends-pr-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
|
|
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
|
|
|
jobs:
|
|
generate-matrix:
|
|
runs-on: ubuntu-latest
|
|
outputs:
|
|
matrix-singlearch: ${{ steps.set-matrix.outputs['matrix-singlearch'] }}
|
|
matrix-multiarch: ${{ steps.set-matrix.outputs['matrix-multiarch'] }}
|
|
matrix-darwin: ${{ steps.set-matrix.outputs['matrix-darwin'] }}
|
|
merge-matrix: ${{ steps.set-matrix.outputs['merge-matrix'] }}
|
|
has-backends-singlearch: ${{ steps.set-matrix.outputs['has-backends-singlearch'] }}
|
|
has-backends-multiarch: ${{ steps.set-matrix.outputs['has-backends-multiarch'] }}
|
|
has-backends-darwin: ${{ steps.set-matrix.outputs['has-backends-darwin'] }}
|
|
has-merges: ${{ steps.set-matrix.outputs['has-merges'] }}
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Setup Bun
|
|
uses: oven-sh/setup-bun@v2
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
bun add js-yaml
|
|
bun add @octokit/core
|
|
|
|
# filters the matrix in backend.yml; splits into single-arch and
|
|
# multi-arch groups so backend-merge-jobs can `needs:` only the latter
|
|
# (matches backend.yml's structure).
|
|
- name: Filter matrix for changed backends
|
|
id: set-matrix
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
GITHUB_EVENT_PATH: ${{ github.event_path }}
|
|
run: bun run scripts/changed-backends.js
|
|
|
|
backend-jobs-multiarch:
|
|
needs: generate-matrix
|
|
uses: ./.github/workflows/backend_build.yml
|
|
if: needs.generate-matrix.outputs['has-backends-multiarch'] == 'true'
|
|
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 }}
|
|
builder-base-image: ${{ matrix.builder-base-image || '' }}
|
|
base-image: ${{ matrix.base-image }}
|
|
backend: ${{ matrix.backend }}
|
|
dockerfile: ${{ matrix.dockerfile }}
|
|
skip-drivers: ${{ matrix.skip-drivers }}
|
|
context: ${{ matrix.context }}
|
|
ubuntu-version: ${{ matrix.ubuntu-version }}
|
|
amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
|
|
secrets:
|
|
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
|
|
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
|
|
strategy:
|
|
fail-fast: true
|
|
max-parallel: 8
|
|
matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-multiarch']) }}
|
|
backend-jobs-singlearch:
|
|
needs: generate-matrix
|
|
uses: ./.github/workflows/backend_build.yml
|
|
if: needs.generate-matrix.outputs['has-backends-singlearch'] == 'true'
|
|
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 }}
|
|
builder-base-image: ${{ matrix.builder-base-image || '' }}
|
|
base-image: ${{ matrix.base-image }}
|
|
backend: ${{ matrix.backend }}
|
|
dockerfile: ${{ matrix.dockerfile }}
|
|
skip-drivers: ${{ matrix.skip-drivers }}
|
|
context: ${{ matrix.context }}
|
|
ubuntu-version: ${{ matrix.ubuntu-version }}
|
|
amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
|
|
secrets:
|
|
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
|
|
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
|
|
strategy:
|
|
fail-fast: true
|
|
max-parallel: 8
|
|
matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch']) }}
|
|
backend-merge-jobs:
|
|
needs: [generate-matrix, backend-jobs-multiarch]
|
|
# backend_merge.yml's push-side steps are all gated on
|
|
# github.event_name != 'pull_request', so on a PR the merge job would
|
|
# do nothing. Skip it entirely to avoid spinning up an empty runner.
|
|
if: github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges'] == 'true'
|
|
uses: ./.github/workflows/backend_merge.yml
|
|
with:
|
|
tag-latest: ${{ matrix.tag-latest }}
|
|
tag-suffix: ${{ matrix.tag-suffix }}
|
|
secrets:
|
|
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
|
|
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
|
|
strategy:
|
|
fail-fast: false
|
|
matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix']) }}
|
|
backend-jobs-darwin:
|
|
needs: generate-matrix
|
|
uses: ./.github/workflows/backend_build_darwin.yml
|
|
if: needs.generate-matrix.outputs.has-backends-darwin == 'true'
|
|
with:
|
|
backend: ${{ matrix.backend }}
|
|
build-type: ${{ matrix.build-type }}
|
|
go-version: "1.25.x"
|
|
tag-suffix: ${{ matrix.tag-suffix }}
|
|
lang: ${{ matrix.lang || 'python' }}
|
|
use-pip: ${{ matrix.backend == 'diffusers' }}
|
|
runs-on: "macos-latest"
|
|
secrets:
|
|
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
|
|
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
|
|
strategy:
|
|
fail-fast: true
|
|
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix-darwin) }}
|