LocalAI/.github/workflows/python_backend_build.yml
Ettore Di Giacinto 912c8eff04
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, ) (push) Waiting to run
build container images / core-image-build (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Waiting to run
build container images / core-image-build (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Waiting to run
build container images / core-image-build (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Waiting to run
build container images / core-image-build (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (-aio-gpu-vulkan, ubuntu:22.04, vulkan, true, latest-gpu-vulkan, latest-aio-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Waiting to run
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-bark, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-bark) (push) Waiting to run
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-chatterbox, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-chatterbox) (push) Waiting to run
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-bark, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-bark) (push) Waiting to run
build python backend container images / backend-jobs (bark, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-bark, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-bark) (push) Waiting to run
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-bark, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-bark) (push) Waiting to run
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-bark, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-bark) (push) Waiting to run
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-chatterbox, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-chatterbox) (push) Waiting to run
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-coqui, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-coqui) (push) Waiting to run
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-coqui, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-coqui) (push) Waiting to run
build python backend container images / backend-jobs (coqui, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-coqui, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-coqui) (push) Waiting to run
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-coqui, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-coqui) (push) Waiting to run
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-coqui, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-coqui) (push) Waiting to run
build python backend container images / backend-jobs (diffusers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-diffusers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-diffusers) (push) Waiting to run
build python backend container images / backend-jobs (diffusers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-diffusers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-diffusers) (push) Waiting to run
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-diffusers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-diffusers) (push) Waiting to run
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-diffusers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-diffusers) (push) Waiting to run
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-faster-whisper) (push) Waiting to run
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-faster-whisper) (push) Waiting to run
build python backend container images / backend-jobs (faster-whisper, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-faster-whisper) (push) Waiting to run
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-faster-whisper) (push) Waiting to run
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-faster-whisper, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-faster-whisper) (push) Waiting to run
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-kokoro, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-kokoro) (push) Waiting to run
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-kokoro, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-kokoro) (push) Waiting to run
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-kokoro, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-kokoro) (push) Waiting to run
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-kokoro, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-kokoro) (push) Waiting to run
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-rerankers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-rerankers) (push) Waiting to run
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-rerankers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-rerankers) (push) Waiting to run
build python backend container images / backend-jobs (rerankers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-rerankers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-rerankers) (push) Waiting to run
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-rerankers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-rerankers) (push) Waiting to run
build python backend container images / backend-jobs (kokoro, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-kokoro, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-kokoro) (push) Waiting to run
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-rerankers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-rerankers) (push) Waiting to run
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-transformers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-transformers) (push) Waiting to run
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-transformers, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-transformers) (push) Waiting to run
build python backend container images / backend-jobs (transformers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-transformers, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-transformers) (push) Waiting to run
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-transformers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-transformers) (push) Waiting to run
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-transformers, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-transformers) (push) Waiting to run
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-vllm, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f16-vllm) (push) Waiting to run
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-vllm, linux/amd64, ubuntu-latest, true, -gpu-intel-sycl-f32-vllm) (push) Waiting to run
build python backend container images / backend-jobs (vllm, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-vllm, linux/amd64, ubuntu-latest, true, -gpu-rocm-hipblas-vllm) (push) Waiting to run
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-vllm, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-11-vllm) (push) Waiting to run
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-vllm, linux/amd64, ubuntu-latest, true, -gpu-nvidia-cuda-12-vllm) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run
chore(ci): use public runner for extra backends (#5657)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-06-16 08:21:18 +02:00

244 lines
No EOL
8.8 KiB
YAML

---
name: 'build python backend container images (reusable)'
on:
workflow_call:
inputs:
base-image:
description: 'Base image'
required: true
type: string
build-type:
description: 'Build type'
default: ''
type: string
cuda-major-version:
description: 'CUDA major version'
default: "12"
type: string
cuda-minor-version:
description: 'CUDA minor version'
default: "1"
type: string
platforms:
description: 'Platforms'
default: ''
type: string
tag-latest:
description: 'Tag latest'
default: ''
type: string
latest-image:
description: 'Tag latest'
default: ''
type: string
tag-suffix:
description: 'Tag suffix'
default: ''
type: string
runs-on:
description: 'Runs on'
required: true
default: ''
type: string
backend:
description: 'Backend to build'
required: true
type: string
secrets:
dockerUsername:
required: true
dockerPassword:
required: true
quayUsername:
required: true
quayPassword:
required: true
jobs:
reusable_python_backend-build:
runs-on: ${{ inputs.runs-on }}
steps:
- name: Free Disk Space (Ubuntu)
if: inputs.runs-on == 'ubuntu-latest'
uses: jlumbroso/free-disk-space@main
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: true
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: true
swap-storage: true
- name: Force Install GIT latest
run: |
sudo apt-get update \
&& sudo apt-get install -y software-properties-common \
&& sudo apt-get update \
&& sudo add-apt-repository -y ppa:git-core/ppa \
&& sudo apt-get update \
&& sudo apt-get install -y git
- name: Checkout
uses: actions/checkout@v4
- name: Release space from worker
if: inputs.runs-on == 'ubuntu-latest'
run: |
echo "Listing top largest packages"
pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
head -n 30 <<< "${pkgs}"
echo
df -h
echo
sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
sudo apt-get remove --auto-remove android-sdk-platform-tools snapd || true
sudo apt-get purge --auto-remove android-sdk-platform-tools snapd || true
sudo rm -rf /usr/local/lib/android
sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
sudo rm -rf /usr/share/dotnet
sudo apt-get remove -y '^mono-.*' || true
sudo apt-get remove -y '^ghc-.*' || true
sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
sudo apt-get remove -y 'php.*' || true
sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
sudo apt-get remove -y '^google-.*' || true
sudo apt-get remove -y azure-cli || true
sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
sudo apt-get remove -y '^gfortran-.*' || true
sudo apt-get remove -y microsoft-edge-stable || true
sudo apt-get remove -y firefox || true
sudo apt-get remove -y powershell || true
sudo apt-get remove -y r-base-core || true
sudo apt-get autoremove -y
sudo apt-get clean
echo
echo "Listing top largest packages"
pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
head -n 30 <<< "${pkgs}"
echo
sudo rm -rfv build || true
sudo rm -rf /usr/share/dotnet || true
sudo rm -rf /opt/ghc || true
sudo rm -rf "/usr/local/share/boost" || true
sudo rm -rf "$AGENT_TOOLSDIRECTORY" || true
df -h
- name: Docker meta
id: meta
if: github.event_name != 'pull_request'
uses: docker/metadata-action@v5
with:
images: |
quay.io/go-skynet/local-ai-backends
localai/localai-backends
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
- name: Docker meta for PR
id: meta_pull_request
if: github.event_name == 'pull_request'
uses: docker/metadata-action@v5
with:
images: |
quay.io/go-skynet/ci-tests
tags: |
type=ref,event=branch,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=semver,pattern={{raw}},suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=sha,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
## End testing image
- name: Set up QEMU
uses: docker/setup-qemu-action@master
with:
platforms: all
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@master
- name: Login to DockerHub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.dockerUsername }}
password: ${{ secrets.dockerPassword }}
- name: Login to Quay.io
# if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: quay.io
username: ${{ secrets.quayUsername }}
password: ${{ secrets.quayPassword }}
- name: Build and push
uses: docker/build-push-action@v6
if: github.event_name != 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
context: ./backend
file: ./backend/Dockerfile.python
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
- name: Build and push (PR)
uses: docker/build-push-action@v6
if: github.event_name == 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
context: ./backend
file: ./backend/Dockerfile.python
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: true
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
- name: Cleanup
run: |
docker builder prune -f
docker system prune --force --volumes --all
- name: Latest tag
if: github.event_name != 'pull_request' && inputs.latest-image != '' && github.ref_type == 'tag'
run: |
docker pull localai/localai-backends:${{ steps.meta.outputs.version }}
docker tag localai/localai-backends:${{ steps.meta.outputs.version }} localai/localai-backends:${{ inputs.latest-image }}
docker push localai/localai-backends:${{ inputs.latest-image }}
docker pull quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }}
docker tag quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }} quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
docker push quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
- name: job summary
run: |
echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY