mirror of
https://github.com/mudler/LocalAI.git
synced 2026-04-30 20:15:35 -04:00
9a7f5e68bd
macOS runners can't use the registry-backed BuildKit cache (no Docker daemon), so every darwin matrix run was paying full cost for brew installs, Go module downloads, llama.cpp recompiles and Python wheel resolution. Wires actions/cache@v4 into the reusable workflow for four caches: - Go modules + build cache (setup-go cache: true), shared across matrix - Homebrew downloads + selected /opt/homebrew/Cellar entries, with HOMEBREW_NO_AUTO_UPDATE so restored Cellar paths stay stable - ccache for the llama-cpp CMake variants, keyed on the pinned LLAMA_VERSION; CMAKE_*_COMPILER_LAUNCHER is exported via GITHUB_ENV so backend/cpp/llama-cpp/Makefile picks it up without script changes - Python uv + pip wheel cache, keyed by backend + ISO week — same one-cold-rebuild-per-week cadence as the Linux DEPS_REFRESH Read/write semantics match the existing BuildKit policy: every run restores, only master/tag pushes save, so PRs can't pollute master's warm cache. Documents the new caches and the macOS-specific constraints in .agents/ci-caching.md. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-7[1m] [Claude Code]
272 lines
9.9 KiB
YAML
272 lines
9.9 KiB
YAML
---
|
|
name: 'build darwin python backend container images (reusable)'
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
backend:
|
|
description: 'Backend to build'
|
|
required: true
|
|
type: string
|
|
build-type:
|
|
description: 'Build type (e.g., mps)'
|
|
default: ''
|
|
type: string
|
|
use-pip:
|
|
description: 'Use pip to install dependencies'
|
|
default: false
|
|
type: boolean
|
|
lang:
|
|
description: 'Programming language (e.g. go)'
|
|
default: 'python'
|
|
type: string
|
|
go-version:
|
|
description: 'Go version to use'
|
|
default: '1.24.x'
|
|
type: string
|
|
tag-suffix:
|
|
description: 'Tag suffix for the built image'
|
|
required: true
|
|
type: string
|
|
runs-on:
|
|
description: 'Runner to use'
|
|
default: 'macOS-14'
|
|
type: string
|
|
secrets:
|
|
dockerUsername:
|
|
required: false
|
|
dockerPassword:
|
|
required: false
|
|
quayUsername:
|
|
required: true
|
|
quayPassword:
|
|
required: true
|
|
|
|
jobs:
|
|
darwin-backend-build:
|
|
runs-on: ${{ inputs.runs-on }}
|
|
strategy:
|
|
matrix:
|
|
go-version: ['${{ inputs.go-version }}']
|
|
env:
|
|
# Keep the brew Cellar stable across cache restores. Without these,
|
|
# `brew install` would auto-update brew itself and re-link formulas,
|
|
# mutating the very paths the cache just restored.
|
|
HOMEBREW_NO_AUTO_UPDATE: '1'
|
|
HOMEBREW_NO_INSTALL_CLEANUP: '1'
|
|
HOMEBREW_NO_ANALYTICS: '1'
|
|
steps:
|
|
- name: Clone
|
|
uses: actions/checkout@v6
|
|
with:
|
|
submodules: true
|
|
|
|
- name: Setup Go ${{ matrix.go-version }}
|
|
uses: actions/setup-go@v5
|
|
with:
|
|
go-version: ${{ matrix.go-version }}
|
|
# Caches ~/go/pkg/mod and ~/Library/Caches/go-build keyed on go.sum.
|
|
# Shared across every darwin matrix entry — first job in a run warms
|
|
# it, the rest hit warm.
|
|
cache: true
|
|
|
|
# You can test your matrix by printing the current Go version
|
|
- name: Display Go version
|
|
run: go version
|
|
|
|
# ---- Homebrew cache ----
|
|
# macOS runners have no Docker daemon, so the BuildKit registry cache used
|
|
# for Linux backend images (see .agents/ci-caching.md) doesn't apply here.
|
|
# We cache the brew downloads + Cellar entries for the formulas we install
|
|
# below. Read on every run, write only on master/tag pushes — same policy
|
|
# as the Linux registry cache.
|
|
- name: Restore Homebrew cache
|
|
id: brew-cache
|
|
uses: actions/cache/restore@v4
|
|
with:
|
|
path: |
|
|
~/Library/Caches/Homebrew/downloads
|
|
/opt/homebrew/Cellar/protobuf
|
|
/opt/homebrew/Cellar/grpc
|
|
/opt/homebrew/Cellar/protoc-gen-go
|
|
/opt/homebrew/Cellar/protoc-gen-go-grpc
|
|
/opt/homebrew/Cellar/libomp
|
|
/opt/homebrew/Cellar/llvm
|
|
/opt/homebrew/Cellar/ccache
|
|
key: brew-${{ runner.os }}-${{ runner.arch }}-v1-${{ hashFiles('.github/workflows/backend_build_darwin.yml') }}
|
|
|
|
- name: Dependencies
|
|
run: |
|
|
# ccache is always installed (used by the llama-cpp variant build) so
|
|
# the brew cache content stays stable across every backend in the
|
|
# matrix — they all share one cache key.
|
|
brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm ccache
|
|
|
|
- name: Save Homebrew cache
|
|
if: github.event_name != 'pull_request' && steps.brew-cache.outputs.cache-hit != 'true'
|
|
uses: actions/cache/save@v4
|
|
with:
|
|
path: |
|
|
~/Library/Caches/Homebrew/downloads
|
|
/opt/homebrew/Cellar/protobuf
|
|
/opt/homebrew/Cellar/grpc
|
|
/opt/homebrew/Cellar/protoc-gen-go
|
|
/opt/homebrew/Cellar/protoc-gen-go-grpc
|
|
/opt/homebrew/Cellar/libomp
|
|
/opt/homebrew/Cellar/llvm
|
|
/opt/homebrew/Cellar/ccache
|
|
key: brew-${{ runner.os }}-${{ runner.arch }}-v1-${{ hashFiles('.github/workflows/backend_build_darwin.yml') }}
|
|
|
|
# ---- ccache for llama.cpp CMake builds ----
|
|
# Three CMake variants (fallback, grpc, rpc-server) compile the same
|
|
# llama.cpp source tree with overlapping flags — ccache dedupes object
|
|
# files across them. Key on the pinned LLAMA_VERSION so a pin bump
|
|
# invalidates cleanly; restore-keys fall back to the latest entry for the
|
|
# same pin so unchanged TUs stay warm even when the cache is fresh.
|
|
- name: Compute llama.cpp version
|
|
if: inputs.backend == 'llama-cpp'
|
|
id: llama-version
|
|
run: |
|
|
version=$(grep '^LLAMA_VERSION' backend/cpp/llama-cpp/Makefile | head -1 | cut -d= -f2 | cut -d'?' -f1 | tr -d ' ')
|
|
echo "version=${version}" >> "$GITHUB_OUTPUT"
|
|
|
|
- name: Restore ccache
|
|
if: inputs.backend == 'llama-cpp'
|
|
id: ccache-cache
|
|
uses: actions/cache/restore@v4
|
|
with:
|
|
path: ~/Library/Caches/ccache
|
|
key: ccache-llama-${{ runner.arch }}-${{ steps.llama-version.outputs.version }}-${{ github.run_id }}
|
|
restore-keys: |
|
|
ccache-llama-${{ runner.arch }}-${{ steps.llama-version.outputs.version }}-
|
|
|
|
- name: Configure ccache
|
|
if: inputs.backend == 'llama-cpp'
|
|
run: |
|
|
mkdir -p "$HOME/Library/Caches/ccache"
|
|
ccache -M 2G
|
|
ccache -z
|
|
# llama-cpp-darwin.sh reads CMAKE_ARGS / CCACHE_DIR from env.
|
|
{
|
|
echo "CMAKE_ARGS=${CMAKE_ARGS:-} -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CXX_COMPILER_LAUNCHER=ccache"
|
|
echo "CCACHE_DIR=$HOME/Library/Caches/ccache"
|
|
} >> "$GITHUB_ENV"
|
|
|
|
# ---- Python wheel cache (uv + pip) ----
|
|
# Mirrors the Linux DEPS_REFRESH cadence (see .agents/ci-caching.md): the
|
|
# ISO-week segment of the cache key forces at most one cold rebuild per
|
|
# backend per week, automatically picking up newer wheels for unpinned
|
|
# deps (torch, mlx, diffusers, …). Restore-keys fall back to the most
|
|
# recent build of the same backend so off-week PRs still hit warm.
|
|
- name: Compute weekly cache bucket
|
|
if: inputs.lang == 'python'
|
|
id: weekly
|
|
run: echo "bucket=$(date -u +%Y-W%V)" >> "$GITHUB_OUTPUT"
|
|
|
|
- name: Restore Python wheel cache
|
|
if: inputs.lang == 'python'
|
|
id: pyenv-cache
|
|
uses: actions/cache/restore@v4
|
|
with:
|
|
path: |
|
|
~/Library/Caches/pip
|
|
~/Library/Caches/uv
|
|
key: pyenv-darwin-${{ inputs.backend }}-${{ steps.weekly.outputs.bucket }}-${{ hashFiles(format('backend/python/{0}/requirements*.txt', inputs.backend)) }}
|
|
restore-keys: |
|
|
pyenv-darwin-${{ inputs.backend }}-
|
|
|
|
- name: Build ${{ inputs.backend }}-darwin
|
|
run: |
|
|
make protogen-go
|
|
BACKEND=${{ inputs.backend }} BUILD_TYPE=${{ inputs.build-type }} USE_PIP=${{ inputs.use-pip }} make build-darwin-${{ inputs.lang }}-backend
|
|
|
|
- name: ccache stats
|
|
if: inputs.backend == 'llama-cpp'
|
|
run: ccache -s
|
|
|
|
- name: Save ccache
|
|
if: inputs.backend == 'llama-cpp' && github.event_name != 'pull_request'
|
|
uses: actions/cache/save@v4
|
|
with:
|
|
path: ~/Library/Caches/ccache
|
|
key: ccache-llama-${{ runner.arch }}-${{ steps.llama-version.outputs.version }}-${{ github.run_id }}
|
|
|
|
- name: Save Python wheel cache
|
|
if: inputs.lang == 'python' && github.event_name != 'pull_request' && steps.pyenv-cache.outputs.cache-hit != 'true'
|
|
uses: actions/cache/save@v4
|
|
with:
|
|
path: |
|
|
~/Library/Caches/pip
|
|
~/Library/Caches/uv
|
|
key: pyenv-darwin-${{ inputs.backend }}-${{ steps.weekly.outputs.bucket }}-${{ hashFiles(format('backend/python/{0}/requirements*.txt', inputs.backend)) }}
|
|
|
|
- name: Upload ${{ inputs.backend }}.tar
|
|
uses: actions/upload-artifact@v7
|
|
with:
|
|
name: ${{ inputs.backend }}-tar
|
|
path: backend-images/${{ inputs.backend }}.tar
|
|
|
|
darwin-backend-publish:
|
|
needs: darwin-backend-build
|
|
if: github.event_name != 'pull_request'
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Download ${{ inputs.backend }}.tar
|
|
uses: actions/download-artifact@v8
|
|
with:
|
|
name: ${{ inputs.backend }}-tar
|
|
path: .
|
|
|
|
- name: Install crane
|
|
run: |
|
|
curl -L https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz | tar -xz
|
|
sudo mv crane /usr/local/bin/
|
|
|
|
- name: Log in to DockerHub
|
|
run: |
|
|
echo "${{ secrets.dockerPassword }}" | crane auth login docker.io -u "${{ secrets.dockerUsername }}" --password-stdin
|
|
|
|
- name: Log in to quay.io
|
|
run: |
|
|
echo "${{ secrets.quayPassword }}" | crane auth login quay.io -u "${{ secrets.quayUsername }}" --password-stdin
|
|
|
|
- name: Docker meta
|
|
id: meta
|
|
uses: docker/metadata-action@v6
|
|
with:
|
|
images: |
|
|
localai/localai-backends
|
|
tags: |
|
|
type=ref,event=branch
|
|
type=semver,pattern={{raw}}
|
|
type=sha
|
|
flavor: |
|
|
latest=auto
|
|
suffix=${{ inputs.tag-suffix }},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=${{ inputs.tag-suffix }},onlatest=true
|
|
|
|
- name: Push Docker image (DockerHub)
|
|
run: |
|
|
for tag in $(echo "${{ steps.meta.outputs.tags }}" | tr ',' '\n'); do
|
|
crane push ${{ inputs.backend }}.tar $tag
|
|
done
|
|
|
|
- name: Push Docker image (Quay)
|
|
run: |
|
|
for tag in $(echo "${{ steps.quaymeta.outputs.tags }}" | tr ',' '\n'); do
|
|
crane push ${{ inputs.backend }}.tar $tag
|
|
done
|