mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 13:10:23 -04:00
cb68cd1cf4
ci: pilot per-arch split for faster-whisper and llama-cpp-quantization
Convert two backends from QEMU-emulated multi-arch (linux/amd64,linux/arm64
on a single ubuntu-latest) to native per-arch + manifest-list merge:
- amd64 leg on ubuntu-latest
- arm64 leg on ubuntu-24.04-arm (native, ~5-10x faster than emulated)
- merge job assembles both digests under the final tag via
docker buildx imagetools create
Backends piloted:
- -cpu-faster-whisper (small Python, fast baseline)
- -cpu-llama-cpp-quantization (heavier compile path, stress test)
Infrastructure changes that the rest of Phase 2 (Tasks 2.5+) will reuse:
- .github/backend-matrix.yml entries gain a `platform-tag` field
('amd64'/'arm64') for matrix entries that participate in the split.
Other entries omit it; backend_build.yml already defaults missing
values to '' (empty cache key suffix preserved as cache<suffix>-).
- backend.yml + backend_pr.yml forward `platform-tag` from matrix to
the reusable backend_build.yml.
- scripts/changed-backends.js groups filtered entries by tag-suffix
and emits a `merge-matrix` (plus `has-merges`) for groups of size>=2.
Singletons aren't merged.
- backend.yml + backend_pr.yml gain a `backend-merge-jobs` job that
consumes merge-matrix and calls backend_merge.yml after backend-jobs.
PR variant is also event-gated so the no-op-on-PR merge job doesn't
even start.
The other 34 multi-arch entries are unchanged in this PR -- Task 2.5
fans out the same shape to them once the pilot is observed green.
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>
101 lines
3.8 KiB
YAML
101 lines
3.8 KiB
YAML
name: 'build backend container images (PR-filtered)'
|
|
|
|
on:
|
|
pull_request:
|
|
|
|
concurrency:
|
|
group: ci-backends-pr-${{ github.head_ref || github.ref }}-${{ github.repository }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
generate-matrix:
|
|
runs-on: ubuntu-latest
|
|
outputs:
|
|
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
|
matrix-darwin: ${{ steps.set-matrix.outputs.matrix-darwin }}
|
|
merge-matrix: ${{ steps.set-matrix.outputs['merge-matrix'] }}
|
|
has-backends: ${{ steps.set-matrix.outputs.has-backends }}
|
|
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
|
|
- 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:
|
|
needs: generate-matrix
|
|
uses: ./.github/workflows/backend_build.yml
|
|
if: needs.generate-matrix.outputs.has-backends == '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 }}
|
|
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) }}
|
|
backend-merge-jobs:
|
|
needs: [generate-matrix, backend-jobs]
|
|
# 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: "1.24.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) }}
|