Files
LocalAI/.github/workflows/backend.yml
LocalAI [bot] cb68cd1cf4 ci: pilot per-arch split + manifest merge for faster-whisper and llama-cpp-quantization (#9727)
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>
2026-05-09 00:04:42 +02:00

217 lines
7.9 KiB
YAML

---
name: 'build backend container images'
on:
push:
branches:
- master
tags:
- '*'
schedule:
# Weekly full-matrix rebuild to pick up upstream Python wheel updates
# (torch, transformers, vllm, ...) which most backends pull unpinned.
# The DEPS_REFRESH build-arg in backend_build.yml busts the install
# layer cache on a new ISO week, but only fires when the build runs.
# Path filtering on commit-driven pushes (scripts/changed-backends.js)
# skips untouched backends, so without this cron those images would
# drift on stale wheels indefinitely. C++/Go backends with pinned
# deps cache-hit and finish fast.
#
# Schedule events have no event.ref / event.before, so the script's
# changedFiles==null fallback emits the full matrix automatically —
# no script changes needed.
- cron: '0 6 * * 0' # Sundays 06:00 UTC
workflow_dispatch:
concurrency:
group: ci-backends-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
generate-matrix:
if: github.repository == 'mudler/LocalAI'
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
# Filter the backend matrix from .github/backend-matrix.yml against the
# files changed by this push. Tag pushes set FORCE_ALL=true so the script
# falls through to the full matrix (releases must rebuild everything).
- name: Filter matrix for changed backends
id: set-matrix
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_EVENT_PATH: ${{ github.event_path }}
FORCE_ALL: ${{ startsWith(github.ref, 'refs/tags/') && 'true' || 'false' }}
run: bun run scripts/changed-backends.js
backend-jobs:
needs: generate-matrix
if: needs.generate-matrix.outputs.has-backends == 'true'
uses: ./.github/workflows/backend_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 }}
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:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
fail-fast: false
max-parallel: 8
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
backend-merge-jobs:
needs: [generate-matrix, backend-jobs]
if: 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:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
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
if: needs.generate-matrix.outputs.has-backends-darwin == 'true'
uses: ./.github/workflows/backend_build_darwin.yml
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:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix-darwin) }}
llama-cpp-darwin:
runs-on: macos-latest
strategy:
matrix:
go-version: ['1.25.x']
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Setup Go ${{ matrix.go-version }}
uses: actions/setup-go@v5
with:
go-version: ${{ matrix.go-version }}
cache: false
# You can test your matrix by printing the current Go version
- name: Display Go version
run: go version
- name: Dependencies
run: |
brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm
- name: Build llama-cpp-darwin
run: |
make protogen-go
make backends/llama-cpp-darwin
- name: Upload llama-cpp.tar
uses: actions/upload-artifact@v7
with:
name: llama-cpp-tar
path: backend-images/llama-cpp.tar
llama-cpp-darwin-publish:
needs: llama-cpp-darwin
if: github.event_name != 'pull_request'
runs-on: ubuntu-latest
steps:
- name: Download llama-cpp.tar
uses: actions/download-artifact@v8
with:
name: llama-cpp-tar
path: .
- name: Install crane
run: |
curl -L https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz | tar -xz
sudo mv crane /usr/local/bin/
- name: Log in to DockerHub
run: |
echo "${{ secrets.DOCKERHUB_PASSWORD }}" | crane auth login docker.io -u "${{ secrets.DOCKERHUB_USERNAME }}" --password-stdin
- name: Log in to quay.io
run: |
echo "${{ secrets.LOCALAI_REGISTRY_PASSWORD }}" | crane auth login quay.io -u "${{ secrets.LOCALAI_REGISTRY_USERNAME }}" --password-stdin
- name: Docker meta
id: meta
uses: docker/metadata-action@v6
with:
images: |
localai/localai-backends
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=auto
suffix=-metal-darwin-arm64-llama-cpp,onlatest=true
- name: Docker meta
id: quaymeta
uses: docker/metadata-action@v6
with:
images: |
quay.io/go-skynet/local-ai-backends
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=auto
suffix=-metal-darwin-arm64-llama-cpp,onlatest=true
- name: Push Docker image (DockerHub)
run: |
for tag in $(echo "${{ steps.meta.outputs.tags }}" | tr ',' '\n'); do
crane push llama-cpp.tar $tag
done
- name: Push Docker image (Quay)
run: |
for tag in $(echo "${{ steps.quaymeta.outputs.tags }}" | tr ',' '\n'); do
crane push llama-cpp.tar $tag
done