mudler/LocalAI
27 workflows · maturity 67% · 11 patterns · GitHub ↗
Practices
✓ Matrix✓ Permissions✓ Security scan○ AI review○ Cache✓ Concurrency✓ Reusable workflows
Detected patterns
Security dimensions
Tools: github/codeql-action/upload-sarif, securego/gosec
Workflows (27)
backend matrix .github/workflows/backend.yml
View raw YAML
---
name: 'build backend container images'
on:
push:
branches:
- master
tags:
- '*'
concurrency:
group: ci-backends-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
backend-jobs:
if: github.repository == 'mudler/LocalAI'
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 }}
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 }}
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: ${{ github.event_name != 'pull_request' && 6 || 4 }}
matrix:
include:
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-diffusers'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-diffusers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-chatterbox'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "chatterbox"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-moonshine'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "moonshine"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-whisperx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "whisperx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-ace-step'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "ace-step"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-trl'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "trl"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-llama-cpp-quantization'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "llama-cpp-quantization"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-mlx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "mlx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-mlx-vlm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "mlx-vlm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-mlx-audio'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "mlx-audio"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-mlx-distributed'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "mlx-distributed"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# CUDA 12 builds
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-vibevoice'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-qwen-asr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-nemo'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "nemo"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-fish-speech'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-faster-qwen3-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-voxcpm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voxcpm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-pocket-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-rerankers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "rerankers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-llama-cpp'
runs-on: 'bigger-runner'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-vllm'
runs-on: 'arc-runner-set'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "vllm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-vllm-omni'
runs-on: 'arc-runner-set'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "vllm-omni"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-transformers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "transformers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-ace-step'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "ace-step"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-trl'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "trl"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-kokoro'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "kokoro"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-faster-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-whisper"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-whisperx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisperx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "9"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-coqui'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "coqui"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-outetts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "outetts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-chatterbox'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "chatterbox"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-moonshine'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "moonshine"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-mlx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-mlx-vlm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-vlm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-mlx-audio'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-audio"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-mlx-distributed'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-distributed"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-rfdetr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "rfdetr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-neutts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "neutts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# cuda 13
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-rerankers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "rerankers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-vibevoice'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-qwen-asr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-nemo'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "nemo"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-fish-speech'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-faster-qwen3-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-voxcpm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voxcpm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-pocket-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-llama-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-llama-cpp'
base-image: "ubuntu:24.04"
runs-on: 'ubuntu-24.04-arm'
ubuntu-version: '2404'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-transformers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "transformers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-diffusers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-ace-step'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "ace-step"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-trl'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "trl"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-vibevoice'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-qwen-asr'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-qwen-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-fish-speech'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-pocket-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-chatterbox'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "chatterbox"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-diffusers'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "mlx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-vlm'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "mlx-vlm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-audio'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "mlx-audio"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'l4t'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-distributed'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
ubuntu-version: '2404'
backend: "mlx-distributed"
dockerfile: "./backend/Dockerfile.python"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-kokoro'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "kokoro"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-faster-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "faster-whisper"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-whisperx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisperx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-chatterbox'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "chatterbox"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-moonshine'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "moonshine"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-mlx'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-mlx-vlm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-vlm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-mlx-audio'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-audio"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-mlx-distributed'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "mlx-distributed"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-stablediffusion-ggml'
base-image: "ubuntu:24.04"
ubuntu-version: '2404'
runs-on: 'ubuntu-24.04-arm'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-whisper'
base-image: "ubuntu:24.04"
ubuntu-version: '2404'
runs-on: 'ubuntu-24.04-arm'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-acestep-cpp'
base-image: "ubuntu:24.04"
ubuntu-version: '2404'
runs-on: 'ubuntu-24.04-arm'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-rfdetr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "rfdetr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# hipblas builds
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-rerankers'
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "rerankers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-llama-cpp'
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-vllm'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "vllm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-vllm-omni'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "vllm-omni"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-transformers'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "transformers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-diffusers'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-ace-step'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "ace-step"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# ROCm additional backends
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-kokoro'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "kokoro"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-vibevoice'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-qwen-asr'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-nemo'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "nemo"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-qwen-tts'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-fish-speech'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-voxcpm'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "voxcpm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-pocket-tts'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-faster-whisper'
runs-on: 'bigger-runner'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "faster-whisper"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-whisperx'
runs-on: 'bigger-runner'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "whisperx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-coqui'
runs-on: 'bigger-runner'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "coqui"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# sycl builds
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-rerankers'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "rerankers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-llama-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-llama-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-vllm'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "vllm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-transformers'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "transformers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-diffusers'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-ace-step'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "ace-step"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-vibevoice'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-qwen-asr'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-qwen-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-fish-speech'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-faster-qwen3-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "faster-qwen3-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-pocket-tts'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-kokoro'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "kokoro"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-mlx'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "mlx"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-mlx-vlm'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "mlx-vlm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-mlx-audio'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "mlx-audio"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-mlx-distributed'
runs-on: 'ubuntu-24.04-arm'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
skip-drivers: 'true'
backend: "mlx-distributed"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
# SYCL additional backends
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-kokoro'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "kokoro"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-faster-whisper'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "faster-whisper"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-vibevoice'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-qwen-asr'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-nemo'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "nemo"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-qwen-tts'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-fish-speech'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-voxcpm'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "voxcpm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-pocket-tts'
runs-on: 'arc-runner-set'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-coqui'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "coqui"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# piper
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-piper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "piper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-llama-cpp'
runs-on: 'bigger-runner'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-llama-cpp'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2204'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-llama-cpp'
runs-on: 'bigger-runner'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "llama-cpp"
dockerfile: "./backend/Dockerfile.llama-cpp"
context: "./"
ubuntu-version: '2404'
# Stablediffusion-ggml
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-stablediffusion-ggml'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-stablediffusion-ggml'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "stablediffusion-ggml"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2204'
# whisper
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-whisper'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-whisper'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-whisper'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-whisper'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2204'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-whisper'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
runs-on: 'ubuntu-latest'
skip-drivers: 'false'
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# acestep-cpp
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-acestep-cpp'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2204'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-acestep-cpp'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
runs-on: 'ubuntu-latest'
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# voxtral
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-voxtral'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voxtral"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
#opus
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-opus'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "opus"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
#silero-vad
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-silero-vad'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "silero-vad"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# local-store
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-local-store'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "local-store"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# rfdetr
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-rfdetr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "rfdetr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'intel'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-rfdetr'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "rfdetr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-rfdetr'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "rfdetr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-chatterbox'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "chatterbox"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2204'
# runs out of space on the runner
# - build-type: 'hipblas'
# cuda-major-version: ""
# cuda-minor-version: ""
# platforms: 'linux/amd64'
# tag-latest: 'auto'
# tag-suffix: '-gpu-hipblas-rfdetr'
# base-image: "rocm/dev-ubuntu-24.04:6.4.4"
# runs-on: 'ubuntu-latest'
# skip-drivers: 'false'
# backend: "rfdetr"
# dockerfile: "./backend/Dockerfile.python"
# context: "./"
# kitten-tts
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-kitten-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "kitten-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
# neutts
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-neutts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "neutts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-neutts'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
skip-drivers: 'false'
backend: "neutts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-vibevoice'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "vibevoice"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-qwen-asr'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-asr"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-nemo'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "nemo"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-qwen-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "qwen-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-fish-speech'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "fish-speech"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-voxcpm'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voxcpm"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-pocket-tts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "pocket-tts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-outetts'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'true'
backend: "outetts"
dockerfile: "./backend/Dockerfile.python"
context: "./"
ubuntu-version: '2404'
backend-jobs-darwin:
uses: ./.github/workflows/backend_build_darwin.yml
strategy:
matrix:
include:
- backend: "diffusers"
tag-suffix: "-metal-darwin-arm64-diffusers"
build-type: "mps"
- backend: "ace-step"
tag-suffix: "-metal-darwin-arm64-ace-step"
build-type: "mps"
- backend: "mlx"
tag-suffix: "-metal-darwin-arm64-mlx"
build-type: "mps"
- backend: "chatterbox"
tag-suffix: "-metal-darwin-arm64-chatterbox"
build-type: "mps"
- backend: "mlx-vlm"
tag-suffix: "-metal-darwin-arm64-mlx-vlm"
build-type: "mps"
- backend: "mlx-audio"
tag-suffix: "-metal-darwin-arm64-mlx-audio"
build-type: "mps"
- backend: "mlx-distributed"
tag-suffix: "-metal-darwin-arm64-mlx-distributed"
build-type: "mps"
- backend: "stablediffusion-ggml"
tag-suffix: "-metal-darwin-arm64-stablediffusion-ggml"
build-type: "metal"
lang: "go"
- backend: "whisper"
tag-suffix: "-metal-darwin-arm64-whisper"
build-type: "metal"
lang: "go"
- backend: "acestep-cpp"
tag-suffix: "-metal-darwin-arm64-acestep-cpp"
build-type: "metal"
lang: "go"
- backend: "voxtral"
tag-suffix: "-metal-darwin-arm64-voxtral"
build-type: "metal"
lang: "go"
- backend: "vibevoice"
tag-suffix: "-metal-darwin-arm64-vibevoice"
build-type: "mps"
- backend: "qwen-asr"
tag-suffix: "-metal-darwin-arm64-qwen-asr"
build-type: "mps"
- backend: "nemo"
tag-suffix: "-metal-darwin-arm64-nemo"
build-type: "mps"
- backend: "qwen-tts"
tag-suffix: "-metal-darwin-arm64-qwen-tts"
build-type: "mps"
- backend: "fish-speech"
tag-suffix: "-metal-darwin-arm64-fish-speech"
build-type: "mps"
- backend: "voxcpm"
tag-suffix: "-metal-darwin-arm64-voxcpm"
build-type: "mps"
- backend: "pocket-tts"
tag-suffix: "-metal-darwin-arm64-pocket-tts"
build-type: "mps"
- backend: "moonshine"
tag-suffix: "-metal-darwin-arm64-moonshine"
build-type: "mps"
- backend: "whisperx"
tag-suffix: "-metal-darwin-arm64-whisperx"
build-type: "mps"
- backend: "rerankers"
tag-suffix: "-metal-darwin-arm64-rerankers"
build-type: "mps"
- backend: "transformers"
tag-suffix: "-metal-darwin-arm64-transformers"
build-type: "mps"
- backend: "kokoro"
tag-suffix: "-metal-darwin-arm64-kokoro"
build-type: "mps"
- backend: "faster-whisper"
tag-suffix: "-metal-darwin-arm64-faster-whisper"
build-type: "mps"
- backend: "coqui"
tag-suffix: "-metal-darwin-arm64-coqui"
build-type: "mps"
- backend: "rfdetr"
tag-suffix: "-metal-darwin-arm64-rfdetr"
build-type: "mps"
- backend: "kitten-tts"
tag-suffix: "-metal-darwin-arm64-kitten-tts"
build-type: "mps"
- backend: "piper"
tag-suffix: "-metal-darwin-arm64-piper"
build-type: "metal"
lang: "go"
- backend: "opus"
tag-suffix: "-metal-darwin-arm64-opus"
build-type: "metal"
lang: "go"
- backend: "silero-vad"
tag-suffix: "-metal-darwin-arm64-silero-vad"
build-type: "metal"
lang: "go"
- backend: "local-store"
tag-suffix: "-metal-darwin-arm64-local-store"
build-type: "metal"
lang: "go"
- backend: "llama-cpp-quantization"
tag-suffix: "-metal-darwin-arm64-llama-cpp-quantization"
build-type: "mps"
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 }}
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
backend_build .github/workflows/backend_build.yml
View raw YAML
---
name: 'build 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
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
context:
description: 'Build context'
required: true
type: string
dockerfile:
description: 'Build Dockerfile'
required: true
type: string
skip-drivers:
description: 'Skip drivers'
default: 'false'
type: string
ubuntu-version:
description: 'Ubuntu version'
required: false
default: '2204'
type: string
secrets:
dockerUsername:
required: false
dockerPassword:
required: false
quayUsername:
required: true
quayPassword:
required: true
jobs:
backend-build:
runs-on: ${{ inputs.runs-on }}
env:
quay_username: ${{ secrets.quayUsername }}
steps:
- name: Free Disk Space (Ubuntu)
if: inputs.runs-on == 'ubuntu-latest'
uses: jlumbroso/free-disk-space@main
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: true
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: true
swap-storage: true
- name: Force Install GIT latest
run: |
sudo apt-get update \
&& sudo apt-get install -y software-properties-common \
&& sudo apt-get update \
&& sudo add-apt-repository -y ppa:git-core/ppa \
&& sudo apt-get update \
&& sudo apt-get install -y git
- name: Checkout
uses: actions/checkout@v6
- name: Release space from worker
if: inputs.runs-on == 'ubuntu-latest'
run: |
echo "Listing top largest packages"
pkgs=$(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 "$AGENT_TOOLSDIRECTORY" || true
df -h
- name: Docker meta
id: meta
if: github.event_name != 'pull_request'
uses: docker/metadata-action@v6
with:
images: |
quay.io/go-skynet/local-ai-backends
localai/localai-backends
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }},onlatest=true
- name: Docker meta for PR
id: meta_pull_request
if: github.event_name == 'pull_request'
uses: docker/metadata-action@v6
with:
images: |
quay.io/go-skynet/ci-tests
tags: |
type=ref,event=branch,suffix=${{ 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 }},onlatest=true
## 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@v4
with:
username: ${{ secrets.dockerUsername }}
password: ${{ secrets.dockerPassword }}
- name: Login to Quay.io
if: ${{ env.quay_username != '' }}
uses: docker/login-action@v4
with:
registry: quay.io
username: ${{ secrets.quayUsername }}
password: ${{ secrets.quayPassword }}
- name: Build and push
uses: docker/build-push-action@v7
if: github.event_name != 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
SKIP_DRIVERS=${{ inputs.skip-drivers }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
UBUNTU_VERSION=${{ inputs.ubuntu-version }}
context: ${{ inputs.context }}
file: ${{ inputs.dockerfile }}
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@v7
if: github.event_name == 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
SKIP_DRIVERS=${{ inputs.skip-drivers }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
UBUNTU_VERSION=${{ inputs.ubuntu-version }}
context: ${{ inputs.context }}
file: ${{ inputs.dockerfile }}
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: ${{ env.quay_username != '' }}
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
- name: job summary
run: |
echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY
backend_build_darwin matrix .github/workflows/backend_build_darwin.yml
View raw 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 }}']
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 ${{ inputs.backend }}-darwin
run: |
make protogen-go
BACKEND=${{ inputs.backend }} BUILD_TYPE=${{ inputs.build-type }} USE_PIP=${{ inputs.use-pip }} make build-darwin-${{ inputs.lang }}-backend
- name: 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 $tag
done
backend_pr matrix .github/workflows/backend_pr.yml
View raw YAML
name: 'build backend container images (PR-filtered)'
on:
pull_request:
concurrency:
group: ci-backends-pr-${{ 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 }}
has-backends: ${{ steps.set-matrix.outputs.has-backends }}
has-backends-darwin: ${{ steps.set-matrix.outputs.has-backends-darwin }}
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 }}
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 }}
secrets:
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
fail-fast: true
matrix: ${{ fromJson(needs.generate-matrix.outputs.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: ${{ fromJson(needs.generate-matrix.outputs.matrix-darwin) }}
build-test .github/workflows/build-test.yaml
View raw YAML
name: Build test
on:
push:
branches:
- master
pull_request:
jobs:
build-test:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.25
- name: Run GoReleaser
run: |
make dev-dist
launcher-build-darwin:
runs-on: macos-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.25
- name: Build launcher for macOS ARM64
run: |
make build-launcher-darwin
ls -liah dist
- name: Upload macOS launcher artifacts
uses: actions/upload-artifact@v7
with:
name: launcher-macos
path: dist/
retention-days: 30
launcher-build-linux:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.25
- name: Build launcher for Linux
run: |
sudo apt-get update
sudo apt-get install golang gcc libgl1-mesa-dev xorg-dev libxkbcommon-dev
make build-launcher-linux
- name: Upload Linux launcher artifacts
uses: actions/upload-artifact@v7
with:
name: launcher-linux
path: local-ai-launcher-linux.tar.xz
retention-days: 30bump-inference-defaults perms .github/workflows/bump-inference-defaults.yml
View raw YAML
name: Bump inference defaults
on:
schedule:
# Run daily at 06:00 UTC
- cron: '0 6 * * *'
workflow_dispatch: # Allow manual trigger
permissions:
contents: write
pull-requests: write
jobs:
bump:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
- name: Re-fetch inference defaults
run: make generate-force
- name: Check for changes
id: diff
run: |
if git diff --quiet core/config/inference_defaults.json; then
echo "changed=false" >> "$GITHUB_OUTPUT"
else
echo "changed=true" >> "$GITHUB_OUTPUT"
fi
- name: Create Pull Request
if: steps.diff.outputs.changed == 'true'
uses: peter-evans/create-pull-request@v8
with:
commit-message: "chore: bump inference defaults from unsloth"
title: "chore: bump inference defaults from unsloth"
body: |
Auto-generated update of `core/config/inference_defaults.json` from
[unsloth's inference_defaults.json](https://github.com/unslothai/unsloth/blob/main/studio/backend/assets/configs/inference_defaults.json).
This PR was created automatically by the `bump-inference-defaults` workflow.
branch: chore/bump-inference-defaults
delete-branch: true
labels: automated
bump_deps matrix .github/workflows/bump_deps.yaml
View raw YAML
name: Bump Backend dependencies
on:
schedule:
- cron: 0 20 * * *
workflow_dispatch:
jobs:
bump-backends:
if: github.repository == 'mudler/LocalAI'
strategy:
fail-fast: false
matrix:
include:
- repository: "ggml-org/llama.cpp"
variable: "LLAMA_VERSION"
branch: "master"
file: "backend/cpp/llama-cpp/Makefile"
- repository: "ggml-org/whisper.cpp"
variable: "WHISPER_CPP_VERSION"
branch: "master"
file: "backend/go/whisper/Makefile"
- repository: "leejet/stable-diffusion.cpp"
variable: "STABLEDIFFUSION_GGML_VERSION"
branch: "master"
file: "backend/go/stablediffusion-ggml/Makefile"
- repository: "mudler/go-piper"
variable: "PIPER_VERSION"
branch: "master"
file: "backend/go/piper/Makefile"
- repository: "antirez/voxtral.c"
variable: "VOXTRAL_VERSION"
branch: "main"
file: "backend/go/voxtral/Makefile"
- repository: "ace-step/acestep.cpp"
variable: "ACESTEP_CPP_VERSION"
branch: "master"
file: "backend/go/acestep-cpp/Makefile"
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Bump dependencies 🔧
id: bump
run: |
bash .github/bump_deps.sh ${{ matrix.repository }} ${{ matrix.branch }} ${{ matrix.variable }} ${{ matrix.file }}
{
echo 'message<<EOF'
cat "${{ matrix.variable }}_message.txt"
echo EOF
} >> "$GITHUB_OUTPUT"
{
echo 'commit<<EOF'
cat "${{ matrix.variable }}_commit.txt"
echo EOF
} >> "$GITHUB_OUTPUT"
rm -rfv ${{ matrix.variable }}_message.txt
rm -rfv ${{ matrix.variable }}_commit.txt
- name: Create Pull Request
uses: peter-evans/create-pull-request@v8
with:
token: ${{ secrets.UPDATE_BOT_TOKEN }}
push-to-fork: ci-forks/LocalAI
commit-message: ':arrow_up: Update ${{ matrix.repository }}'
title: 'chore: :arrow_up: Update ${{ matrix.repository }} to `${{ steps.bump.outputs.commit }}`'
branch: "update/${{ matrix.variable }}"
body: ${{ steps.bump.outputs.message }}
signoff: true
bump_docs matrix .github/workflows/bump_docs.yaml
View raw YAML
name: Bump Documentation
on:
schedule:
- cron: 0 20 * * *
workflow_dispatch:
jobs:
bump-docs:
if: github.repository == 'mudler/LocalAI'
strategy:
fail-fast: false
matrix:
include:
- repository: "mudler/LocalAI"
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Bump dependencies 🔧
run: |
bash .github/bump_docs.sh ${{ matrix.repository }}
- name: Create Pull Request
uses: peter-evans/create-pull-request@v8
with:
token: ${{ secrets.UPDATE_BOT_TOKEN }}
push-to-fork: ci-forks/LocalAI
commit-message: ':arrow_up: Update docs version ${{ matrix.repository }}'
title: 'docs: :arrow_up: update docs version ${{ matrix.repository }}'
branch: "update/docs"
body: Bump of ${{ matrix.repository }} version inside docs
signoff: true
checksum_checker .github/workflows/checksum_checker.yaml
View raw YAML
name: Check if checksums are up-to-date
on:
schedule:
- cron: 0 20 * * *
workflow_dispatch:
jobs:
checksum_check:
if: github.repository == 'mudler/LocalAI'
runs-on: ubuntu-latest
steps:
- 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
- uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y pip wget
pip install huggingface_hub
- name: 'Setup yq'
uses: dcarbone/install-yq-action@v1.3.1
with:
version: 'v4.44.2'
download-compressed: true
force: true
- name: Checksum checker 🔧
run: |
export HF_HOME=/hf_cache
sudo mkdir /hf_cache
sudo chmod 777 /hf_cache
bash .github/checksum_checker.sh gallery/index.yaml
- name: Create Pull Request
uses: peter-evans/create-pull-request@v8
with:
token: ${{ secrets.UPDATE_BOT_TOKEN }}
push-to-fork: ci-forks/LocalAI
commit-message: ':arrow_up: Checksum updates in gallery/index.yaml'
title: 'chore(model-gallery): :arrow_up: update checksum'
branch: "update/checksum"
body: Updating checksums in gallery/index.yaml
signoff: true
deploy-explorer .github/workflows/deploy-explorer.yaml
View raw YAML
name: Explorer deployment
on:
push:
branches:
- master
tags:
- 'v*'
concurrency:
group: ci-deploy-${{ github.head_ref || github.ref }}-${{ github.repository }}
jobs:
build-linux:
if: github.repository == 'mudler/LocalAI'
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- uses: actions/setup-go@v5
with:
go-version: '1.21.x'
cache: false
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y wget curl build-essential ffmpeg protobuf-compiler ccache upx-ucl gawk cmake libgmock-dev
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
make protogen-go
- name: Build api
run: |
CGO_ENABLED=0 make build
- name: rm
uses: appleboy/ssh-action@v1.2.5
with:
host: ${{ secrets.EXPLORER_SSH_HOST }}
username: ${{ secrets.EXPLORER_SSH_USERNAME }}
key: ${{ secrets.EXPLORER_SSH_KEY }}
port: ${{ secrets.EXPLORER_SSH_PORT }}
script: |
sudo rm -rf local-ai/ || true
- name: copy file via ssh
uses: appleboy/scp-action@v1.0.0
with:
host: ${{ secrets.EXPLORER_SSH_HOST }}
username: ${{ secrets.EXPLORER_SSH_USERNAME }}
key: ${{ secrets.EXPLORER_SSH_KEY }}
port: ${{ secrets.EXPLORER_SSH_PORT }}
source: "local-ai"
overwrite: true
rm: true
target: ./local-ai
- name: restarting
uses: appleboy/ssh-action@v1.2.5
with:
host: ${{ secrets.EXPLORER_SSH_HOST }}
username: ${{ secrets.EXPLORER_SSH_USERNAME }}
key: ${{ secrets.EXPLORER_SSH_KEY }}
port: ${{ secrets.EXPLORER_SSH_PORT }}
script: |
sudo cp -rfv local-ai/local-ai /usr/bin/local-ai
sudo systemctl restart local-ai
gallery-agent .github/workflows/gallery-agent.yaml
View raw YAML
name: Gallery Agent
on:
schedule:
- cron: '0 */3 * * *' # Run every 4 hours
workflow_dispatch:
inputs:
search_term:
description: 'Search term for models'
required: false
default: 'GGUF'
type: string
limit:
description: 'Maximum number of models to process'
required: false
default: '15'
type: string
quantization:
description: 'Preferred quantization format'
required: false
default: 'Q4_K_M'
type: string
max_models:
description: 'Maximum number of models to add to the gallery'
required: false
default: '1'
type: string
jobs:
gallery-agent:
if: github.repository == 'mudler/LocalAI'
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v6
with:
token: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: '1.21'
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- uses: mudler/localai-github-action@v1.1
with:
model: 'https://huggingface.co/unsloth/Qwen3.5-2B-GGUF'
- name: Run gallery agent
env:
#OPENAI_MODEL: ${{ secrets.OPENAI_MODEL }}
OPENAI_MODE: Qwen3.5-2B-GGUF
OPENAI_BASE_URL: "http://localhost:8080"
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
#OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
SEARCH_TERM: ${{ github.event.inputs.search_term || 'GGUF' }}
LIMIT: ${{ github.event.inputs.limit || '15' }}
QUANTIZATION: ${{ github.event.inputs.quantization || 'Q4_K_M' }}
MAX_MODELS: ${{ github.event.inputs.max_models || '1' }}
run: |
export GALLERY_INDEX_PATH=$PWD/gallery/index.yaml
go run ./.github/gallery-agent
- name: Check for changes
id: check_changes
run: |
if git diff --quiet gallery/index.yaml; then
echo "changes=false" >> $GITHUB_OUTPUT
echo "No changes detected in gallery/index.yaml"
else
echo "changes=true" >> $GITHUB_OUTPUT
echo "Changes detected in gallery/index.yaml"
git diff gallery/index.yaml
fi
- name: Read gallery agent summary
id: read_summary
if: steps.check_changes.outputs.changes == 'true'
run: |
if [ -f "./gallery-agent-summary.json" ]; then
echo "summary_exists=true" >> $GITHUB_OUTPUT
# Extract summary data using jq
echo "search_term=$(jq -r '.search_term' ./gallery-agent-summary.json)" >> $GITHUB_OUTPUT
echo "total_found=$(jq -r '.total_found' ./gallery-agent-summary.json)" >> $GITHUB_OUTPUT
echo "models_added=$(jq -r '.models_added' ./gallery-agent-summary.json)" >> $GITHUB_OUTPUT
echo "quantization=$(jq -r '.quantization' ./gallery-agent-summary.json)" >> $GITHUB_OUTPUT
echo "processing_time=$(jq -r '.processing_time' ./gallery-agent-summary.json)" >> $GITHUB_OUTPUT
# Create a formatted list of added models with URLs
added_models=$(jq -r 'range(0; .added_model_ids | length) as $i | "- [\(.added_model_ids[$i])](\(.added_model_urls[$i]))"' ./gallery-agent-summary.json | tr '\n' '\n')
echo "added_models<<EOF" >> $GITHUB_OUTPUT
echo "$added_models" >> $GITHUB_OUTPUT
echo "EOF" >> $GITHUB_OUTPUT
rm -f ./gallery-agent-summary.json
else
echo "summary_exists=false" >> $GITHUB_OUTPUT
fi
- name: Create Pull Request
if: steps.check_changes.outputs.changes == 'true'
uses: peter-evans/create-pull-request@v8
with:
token: ${{ secrets.UPDATE_BOT_TOKEN }}
push-to-fork: ci-forks/LocalAI
commit-message: 'chore(model gallery): :robot: add new models via gallery agent'
title: 'chore(model gallery): :robot: add ${{ steps.read_summary.outputs.models_added || 0 }} new models via gallery agent'
# Branch has to be unique so PRs are not overriding each other
branch-suffix: timestamp
body: |
This PR was automatically created by the gallery agent workflow.
**Summary:**
- **Search Term:** ${{ steps.read_summary.outputs.search_term || github.event.inputs.search_term || 'GGUF' }}
- **Models Found:** ${{ steps.read_summary.outputs.total_found || 'N/A' }}
- **Models Added:** ${{ steps.read_summary.outputs.models_added || '0' }}
- **Quantization:** ${{ steps.read_summary.outputs.quantization || github.event.inputs.quantization || 'Q4_K_M' }}
- **Processing Time:** ${{ steps.read_summary.outputs.processing_time || 'N/A' }}
**Added Models:**
${{ steps.read_summary.outputs.added_models || '- No models added' }}
**Workflow Details:**
- Triggered by: `${{ github.event_name }}`
- Run ID: `${{ github.run_id }}`
- Commit: `${{ github.sha }}`
signoff: true
delete-branch: true
generate_grpc_cache matrix .github/workflows/generate_grpc_cache.yaml
View raw YAML
name: 'generate and publish GRPC docker caches'
on:
workflow_dispatch:
schedule:
# daily at midnight
- cron: '0 0 * * *'
concurrency:
group: grpc-cache-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
generate_caches:
if: github.repository == 'mudler/LocalAI'
strategy:
matrix:
include:
- grpc-base-image: ubuntu:24.04
runs-on: 'ubuntu-latest'
platforms: 'linux/amd64,linux/arm64'
runs-on: ${{matrix.runs-on}}
steps:
- name: Release space from worker
if: matrix.runs-on == 'ubuntu-latest'
run: |
echo "Listing top largest packages"
pkgs=$(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 || true
sudo apt-get purge --auto-remove android-sdk-platform-tools || 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: 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: Checkout
uses: actions/checkout@v6
- name: Cache GRPC
uses: docker/build-push-action@v7
with:
builder: ${{ steps.buildx.outputs.name }}
# The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
# This means that even the MAKEFLAGS have to be an EXACT match.
# If the build-args are not an EXACT match, it will result in a cache miss, which will require GRPC to be built from scratch.
build-args: |
GRPC_BASE_IMAGE=${{ matrix.grpc-base-image }}
GRPC_MAKEFLAGS=--jobs=4 --output-sync=target
GRPC_VERSION=v1.65.0
context: .
file: ./Dockerfile
cache-to: type=gha,ignore-error=true
cache-from: type=gha
target: grpc
platforms: ${{ matrix.platforms }}
push: false
generate_intel_image matrix .github/workflows/generate_intel_image.yaml
View raw YAML
name: 'generate and publish intel docker caches'
on:
workflow_dispatch:
push:
branches:
- master
concurrency:
group: intel-cache-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
generate_caches:
if: github.repository == 'mudler/LocalAI'
strategy:
matrix:
include:
- base-image: intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04
runs-on: 'arc-runner-set'
platforms: 'linux/amd64'
runs-on: ${{matrix.runs-on}}
steps:
- name: Set up QEMU
uses: docker/setup-qemu-action@master
with:
platforms: all
- name: Login to DockerHub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_PASSWORD }}
- name: Login to quay
if: github.event_name != 'pull_request'
uses: docker/login-action@v4
with:
registry: quay.io
username: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
password: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@master
- name: Checkout
uses: actions/checkout@v6
- name: Cache Intel images
uses: docker/build-push-action@v7
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BASE_IMAGE=${{ matrix.base-image }}
context: .
file: ./Dockerfile
tags: quay.io/go-skynet/intel-oneapi-base:24.04
push: true
target: intel
platforms: ${{ matrix.platforms }}
gh-pages perms .github/workflows/gh-pages.yml
View raw YAML
name: Deploy docs to GitHub Pages
on:
push:
branches:
- master
paths:
- 'docs/**'
- 'gallery/**'
- 'images/**'
- '.github/ci/modelslist.go'
- '.github/workflows/gh-pages.yml'
workflow_dispatch:
permissions:
contents: read
pages: write
id-token: write
concurrency:
group: pages
cancel-in-progress: false
jobs:
build:
runs-on: ubuntu-latest
env:
HUGO_VERSION: "0.146.3"
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0 # needed for enableGitInfo
submodules: true
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: '1.22'
cache: false
- name: Setup Hugo
uses: peaceiris/actions-hugo@v3
with:
hugo-version: ${{ env.HUGO_VERSION }}
extended: true
- name: Setup Pages
id: pages
uses: actions/configure-pages@v5
- name: Generate gallery
run: go run ./.github/ci/modelslist.go ./gallery/index.yaml > docs/static/gallery.html
- name: Build site
working-directory: docs
run: |
mkdir -p layouts/_default
hugo --minify --baseURL "${{ steps.pages.outputs.base_url }}/"
- name: Upload artifact
uses: actions/upload-pages-artifact@v3
with:
path: docs/public
deploy:
environment:
name: github-pages
url: ${{ steps.deployment.outputs.page_url }}
runs-on: ubuntu-latest
needs: build
steps:
- name: Deploy to GitHub Pages
id: deployment
uses: actions/deploy-pages@v4
image matrix .github/workflows/image.yml
View raw YAML
---
name: 'build container images'
on:
push:
branches:
- master
tags:
- '*'
concurrency:
group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
hipblas-jobs:
if: github.repository == 'mudler/LocalAI'
uses: ./.github/workflows/image_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 }}
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
ubuntu-version: ${{ matrix.ubuntu-version }}
ubuntu-codename: ${{ matrix.ubuntu-codename }}
secrets:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
matrix:
include:
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-hipblas'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
grpc-base-image: "ubuntu:24.04"
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
core-image-build:
if: github.repository == 'mudler/LocalAI'
uses: ./.github/workflows/image_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 }}
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
skip-drivers: ${{ matrix.skip-drivers }}
ubuntu-version: ${{ matrix.ubuntu-version }}
ubuntu-codename: ${{ matrix.ubuntu-codename }}
secrets:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
#max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
matrix:
include:
- build-type: ''
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: ''
base-image: "ubuntu:24.04"
runs-on: 'ubuntu-latest'
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'false'
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'vulkan'
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'intel'
platforms: 'linux/amd64'
tag-latest: 'auto'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
grpc-base-image: "ubuntu:24.04"
tag-suffix: '-gpu-intel'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
gh-runner:
if: github.repository == 'mudler/LocalAI'
uses: ./.github/workflows/image_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 }}
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
skip-drivers: ${{ matrix.skip-drivers }}
ubuntu-version: ${{ matrix.ubuntu-version }}
ubuntu-codename: ${{ matrix.ubuntu-codename }}
secrets:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
matrix:
include:
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'true'
ubuntu-version: "2204"
ubuntu-codename: 'jammy'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-cuda-13'
base-image: "ubuntu:24.04"
runs-on: 'ubuntu-24.04-arm'
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'false'
ubuntu-version: '2404'
ubuntu-codename: 'noble'
image-pr matrix .github/workflows/image-pr.yml
View raw YAML
---
name: 'build container images tests'
on:
pull_request:
concurrency:
group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
image-build:
uses: ./.github/workflows/image_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 }}
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
ubuntu-version: ${{ matrix.ubuntu-version }}
secrets:
dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
# Pushing with all jobs in parallel
# eats the bandwidth of all the nodes
max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
fail-fast: false
matrix:
include:
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-gpu-nvidia-cuda-12'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-gpu-nvidia-cuda-13'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-hipblas'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
grpc-base-image: "ubuntu:24.04"
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'sycl'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
grpc-base-image: "ubuntu:24.04"
tag-suffix: 'sycl'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'vulkan'
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'false'
tag-suffix: '-vulkan-core'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
makeflags: "--jobs=4 --output-sync=target"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
tag-latest: 'false'
tag-suffix: '-nvidia-l4t-arm64-cuda-13'
base-image: "ubuntu:24.04"
runs-on: 'ubuntu-24.04-arm'
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'false'
ubuntu-version: '2404'
image_build .github/workflows/image_build.yml
View raw YAML
---
name: 'build container images (reusable)'
on:
workflow_call:
inputs:
base-image:
description: 'Base image'
required: true
type: string
grpc-base-image:
description: 'GRPC Base image, must be a compatible image with base-image'
required: false
default: ''
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: "9"
type: string
platforms:
description: 'Platforms'
default: ''
type: string
tag-latest:
description: 'Tag latest'
default: ''
type: string
tag-suffix:
description: 'Tag suffix'
default: ''
type: string
skip-drivers:
description: 'Skip drivers by default'
default: 'false'
type: string
runs-on:
description: 'Runs on'
required: true
default: ''
type: string
makeflags:
description: 'Make Flags'
required: false
default: '--jobs=4 --output-sync=target'
type: string
ubuntu-version:
description: 'Ubuntu version'
required: false
default: '2204'
type: string
ubuntu-codename:
description: 'Ubuntu codename'
required: false
default: 'noble'
type: string
secrets:
dockerUsername:
required: true
dockerPassword:
required: true
quayUsername:
required: true
quayPassword:
required: true
jobs:
reusable_image-build:
runs-on: ${{ inputs.runs-on }}
steps:
- name: Free Disk Space (Ubuntu)
if: inputs.runs-on == 'ubuntu-latest'
uses: jlumbroso/free-disk-space@main
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: true
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: true
swap-storage: true
- name: Force Install GIT latest
run: |
sudo apt-get update \
&& sudo apt-get install -y software-properties-common \
&& sudo apt-get update \
&& sudo add-apt-repository -y ppa:git-core/ppa \
&& sudo apt-get update \
&& sudo apt-get install -y git
- name: Checkout
uses: actions/checkout@v6
- name: Release space from worker
if: inputs.runs-on == 'ubuntu-latest'
run: |
echo "Listing top largest packages"
pkgs=$(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 "$AGENT_TOOLSDIRECTORY" || true
df -h
- name: Docker meta
id: meta
if: github.event_name != 'pull_request'
uses: docker/metadata-action@v6
with:
images: |
quay.io/go-skynet/local-ai
localai/localai
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }},onlatest=true
- name: Docker meta for PR
id: meta_pull_request
if: github.event_name == 'pull_request'
uses: docker/metadata-action@v6
with:
images: |
quay.io/go-skynet/ci-tests
tags: |
type=ref,event=branch,suffix=localai${{ github.event.number }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=semver,pattern={{raw}},suffix=localai${{ github.event.number }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=sha,suffix=localai${{ github.event.number }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
- 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@v4
with:
username: ${{ secrets.dockerUsername }}
password: ${{ secrets.dockerPassword }}
- name: Login to DockerHub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4
with:
registry: quay.io
username: ${{ secrets.quayUsername }}
password: ${{ secrets.quayPassword }}
- name: Build and push
uses: docker/build-push-action@v7
if: github.event_name != 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
# The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
# This means that even the MAKEFLAGS have to be an EXACT match.
# If the build-args are not an EXACT match, it will result in a cache miss, which will require GRPC to be built from scratch.
# This is why some build args like GRPC_VERSION and MAKEFLAGS are hardcoded
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
GRPC_BASE_IMAGE=${{ inputs.grpc-base-image || inputs.base-image }}
GRPC_MAKEFLAGS=--jobs=4 --output-sync=target
GRPC_VERSION=v1.65.0
MAKEFLAGS=${{ inputs.makeflags }}
SKIP_DRIVERS=${{ inputs.skip-drivers }}
UBUNTU_VERSION=${{ inputs.ubuntu-version }}
UBUNTU_CODENAME=${{ inputs.ubuntu-codename }}
context: .
file: ./Dockerfile
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
### Start testing image
- name: Build and push
uses: docker/build-push-action@v7
if: github.event_name == 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
# The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
# This means that even the MAKEFLAGS have to be an EXACT match.
# If the build-args are not an EXACT match, it will result in a cache miss, which will require GRPC to be built from scratch.
# This is why some build args like GRPC_VERSION and MAKEFLAGS are hardcoded
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
GRPC_BASE_IMAGE=${{ inputs.grpc-base-image || inputs.base-image }}
GRPC_MAKEFLAGS=--jobs=4 --output-sync=target
GRPC_VERSION=v1.65.0
MAKEFLAGS=${{ inputs.makeflags }}
SKIP_DRIVERS=${{ inputs.skip-drivers }}
UBUNTU_VERSION=${{ inputs.ubuntu-version }}
UBUNTU_CODENAME=${{ inputs.ubuntu-codename }}
context: .
file: ./Dockerfile
cache-from: type=gha
platforms: ${{ inputs.platforms }}
#push: true
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
## End testing image
- name: job summary
run: |
echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY
notify-releases .github/workflows/notify-releases.yaml
View raw YAML
name: Release notifications
on:
release:
types:
- published
jobs:
notify-discord:
if: github.repository == 'mudler/LocalAI'
runs-on: ubuntu-latest
env:
RELEASE_BODY: ${{ github.event.release.body }}
RELEASE_TITLE: ${{ github.event.release.name }}
RELEASE_TAG_NAME: ${{ github.event.release.tag_name }}
MODEL_NAME: gemma-3-12b-it-qat
steps:
- uses: mudler/localai-github-action@v1
with:
model: 'gemma-3-12b-it-qat' # Any from models.localai.io, or from huggingface.com with: "huggingface://<repository>/file"
- name: Summarize
id: summarize
run: |
input="$RELEASE_TITLE\b$RELEASE_BODY"
# Define the LocalAI API endpoint
API_URL="http://localhost:8080/chat/completions"
# Create a JSON payload using jq to handle special characters
json_payload=$(jq -n --arg input "$input" '{
model: "'$MODEL_NAME'",
messages: [
{
role: "system",
content: "Write a discord message with a bullet point summary of the release notes."
},
{
role: "user",
content: $input
}
]
}')
# Send the request to LocalAI API
response=$(curl -s -X POST $API_URL \
-H "Content-Type: application/json" \
-d "$json_payload")
# Extract the summary from the response
summary=$(echo $response | jq -r '.choices[0].message.content')
# Print the summary
# -H "Authorization: Bearer $API_KEY" \
{
echo 'message<<EOF'
echo "$summary"
echo EOF
} >> "$GITHUB_OUTPUT"
- name: Discord notification
env:
DISCORD_WEBHOOK: ${{ secrets.DISCORD_WEBHOOK_URL_RELEASE }}
DISCORD_USERNAME: "LocalAI-Bot"
DISCORD_AVATAR: "https://avatars.githubusercontent.com/u/139863280?v=4"
uses: Ilshidur/action-discord@master
with:
args: ${{ steps.summarize.outputs.message }}
release .github/workflows/release.yaml
View raw YAML
name: goreleaser
on:
push:
tags:
- 'v*'
jobs:
goreleaser:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.23
- name: Run GoReleaser
uses: goreleaser/goreleaser-action@v7
with:
version: v2.11.0
args: release --clean
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
launcher-build-darwin:
runs-on: macos-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.23
- name: Build launcher for macOS ARM64
run: |
make build-launcher-darwin
- name: Upload DMG to Release
uses: softprops/action-gh-release@v2
with:
files: ./dist/LocalAI.dmg
launcher-build-linux:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: 1.23
- name: Build launcher for Linux
run: |
sudo apt-get update
sudo apt-get install golang gcc libgl1-mesa-dev xorg-dev libxkbcommon-dev
make build-launcher-linux
- name: Upload Linux launcher artifacts
uses: softprops/action-gh-release@v2
with:
files: ./local-ai-launcher-linux.tar.xz
secscan security .github/workflows/secscan.yaml
View raw YAML
name: "Security Scan"
# Run workflow each time code is pushed to your repository and on a schedule.
# The scheduled workflow runs every at 00:00 on Sunday UTC time.
on:
push:
schedule:
- cron: '0 0 * * 0'
jobs:
tests:
runs-on: ubuntu-latest
env:
GO111MODULE: on
steps:
- name: Checkout Source
uses: actions/checkout@v6
if: ${{ github.actor != 'dependabot[bot]' }}
- name: Run Gosec Security Scanner
if: ${{ github.actor != 'dependabot[bot]' }}
uses: securego/gosec@v2.22.9
with:
# we let the report trigger content trigger a failure using the GitHub Security features.
args: '-no-fail -fmt sarif -out results.sarif ./...'
- name: Upload SARIF file
if: ${{ github.actor != 'dependabot[bot]' }}
uses: github/codeql-action/upload-sarif@v4
with:
# Path to SARIF file relative to the root of the repository
sarif_file: results.sarif
stalebot perms .github/workflows/stalebot.yml
View raw YAML
name: 'Close stale issues and PRs'
permissions:
issues: write
pull-requests: write
on:
schedule:
- cron: '30 1 * * *'
jobs:
stale:
if: github.repository == 'mudler/LocalAI'
runs-on: ubuntu-latest
steps:
- uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # v9
with:
stale-issue-message: 'This issue is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 5 days.'
stale-pr-message: 'This PR is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 10 days.'
close-issue-message: 'This issue was closed because it has been stalled for 5 days with no activity.'
close-pr-message: 'This PR was closed because it has been stalled for 10 days with no activity.'
days-before-issue-stale: 90
days-before-pr-stale: 90
days-before-issue-close: 5
days-before-pr-close: 10
exempt-issue-labels: 'roadmap'
exempt-pr-labels: 'roadmap'
test matrix .github/workflows/test.yml
View raw YAML
---
name: 'tests'
on:
pull_request:
push:
branches:
- master
tags:
- '*'
env:
GRPC_VERSION: v1.65.0
concurrency:
group: ci-tests-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
tests-linux:
runs-on: ubuntu-latest
strategy:
matrix:
go-version: ['1.25.x']
steps:
- name: Free Disk Space (Ubuntu)
uses: jlumbroso/free-disk-space@main
with:
# this might remove tools that are actually needed,
# if set to "true" but frees about 6 GB
tool-cache: true
# all of these default to true, but feel free to set to
# "false" if necessary for your workflow
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: true
swap-storage: true
- name: Release space from worker
run: |
echo "Listing top largest packages"
pkgs=$(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 || true
sudo apt-get purge --auto-remove android-sdk-platform-tools || 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 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
df -h
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Setup Go ${{ matrix.go-version }}
uses: actions/setup-go@v5
with:
go-version: ${{ matrix.go-version }}
cache: false
# You can test your matrix by printing the current Go version
- name: Display Go version
run: go version
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install curl ffmpeg libopus-dev
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: '22'
- name: Build React UI
run: make react-ui
- name: Build backends
run: |
make backends/transformers
mkdir external && mv backends/transformers external/transformers
make backends/llama-cpp backends/local-store backends/silero-vad backends/piper backends/whisper backends/stablediffusion-ggml
- name: Test
run: |
TRANSFORMER_BACKEND=$PWD/external/transformers/run.sh PATH="$PATH:/root/go/bin" GO_TAGS="tts" make --jobs 5 --output-sync=target test
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3.23
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
tests-e2e-container:
runs-on: ubuntu-latest
steps:
- name: Release space from worker
run: |
echo "Listing top largest packages"
pkgs=$(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 || true
sudo apt-get purge --auto-remove android-sdk-platform-tools || 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 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
df -h
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Test
run: |
PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3.23
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
tests-apple:
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: ${{ matrix.go-version }}
cache: false
# You can test your matrix by printing the current Go version
- name: Display Go version
run: go version
- name: Dependencies
run: |
brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm opus
pip install --user --no-cache-dir grpcio-tools grpcio
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: '22'
- name: Build React UI
run: make react-ui
- name: Build llama-cpp-darwin
run: |
make protogen-go
make backends/llama-cpp-darwin
- name: Test
run: |
export C_INCLUDE_PATH=/usr/local/include
export CPLUS_INCLUDE_PATH=/usr/local/include
export CC=/opt/homebrew/opt/llvm/bin/clang
# Used to run the newer GNUMake version from brew that supports --output-sync
export PATH="/opt/homebrew/opt/make/libexec/gnubin:$PATH"
PATH="$PATH:$HOME/go/bin" make protogen-go
PATH="$PATH:$HOME/go/bin" BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3.23
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
test-extra .github/workflows/test-extra.yml
View raw YAML
---
name: 'Tests extras backends'
on:
pull_request:
push:
branches:
- master
tags:
- '*'
concurrency:
group: ci-tests-extra-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
# Requires CUDA
# tests-chatterbox-tts:
# runs-on: ubuntu-latest
# steps:
# - name: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install build-essential ffmpeg
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# sudo apt-get install -y libopencv-dev
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test chatterbox-tts
# run: |
# make --jobs=5 --output-sync=target -C backend/python/chatterbox
# make --jobs=5 --output-sync=target -C backend/python/chatterbox test
tests-transformers:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
sudo apt-get install -y libopencv-dev
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test transformers
run: |
make --jobs=5 --output-sync=target -C backend/python/transformers
make --jobs=5 --output-sync=target -C backend/python/transformers test
tests-rerankers:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
sudo apt-get install -y libopencv-dev
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test rerankers
run: |
make --jobs=5 --output-sync=target -C backend/python/rerankers
make --jobs=5 --output-sync=target -C backend/python/rerankers test
tests-diffusers:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
sudo apt-get install -y libopencv-dev
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test diffusers
run: |
make --jobs=5 --output-sync=target -C backend/python/diffusers
make --jobs=5 --output-sync=target -C backend/python/diffusers test
#tests-vllm:
# runs-on: ubuntu-latest
# steps:
# - name: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install -y build-essential ffmpeg
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# sudo apt-get install -y libopencv-dev
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test vllm backend
# run: |
# make --jobs=5 --output-sync=target -C backend/python/vllm
# make --jobs=5 --output-sync=target -C backend/python/vllm test
# tests-transformers-musicgen:
# runs-on: ubuntu-latest
# steps:
# - name: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install build-essential ffmpeg
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# sudo apt-get install -y libopencv-dev
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test transformers-musicgen
# run: |
# make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen
# make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen test
# tests-bark:
# runs-on: ubuntu-latest
# steps:
# - name: Release space from worker
# 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 || true
# sudo apt-get purge --auto-remove android-sdk-platform-tools || 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: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install build-essential ffmpeg
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# sudo apt-get install -y libopencv-dev
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test bark
# run: |
# make --jobs=5 --output-sync=target -C backend/python/bark
# make --jobs=5 --output-sync=target -C backend/python/bark test
# Below tests needs GPU. Commented out for now
# TODO: Re-enable as soon as we have GPU nodes
# tests-vllm:
# runs-on: ubuntu-latest
# steps:
# - name: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install build-essential ffmpeg
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# sudo apt-get install -y libopencv-dev
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test vllm
# run: |
# make --jobs=5 --output-sync=target -C backend/python/vllm
# make --jobs=5 --output-sync=target -C backend/python/vllm test
tests-coqui:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch espeak espeak-ng python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test coqui
run: |
make --jobs=5 --output-sync=target -C backend/python/coqui
make --jobs=5 --output-sync=target -C backend/python/coqui test
tests-moonshine:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test moonshine
run: |
make --jobs=5 --output-sync=target -C backend/python/moonshine
make --jobs=5 --output-sync=target -C backend/python/moonshine test
tests-pocket-tts:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test pocket-tts
run: |
make --jobs=5 --output-sync=target -C backend/python/pocket-tts
make --jobs=5 --output-sync=target -C backend/python/pocket-tts test
tests-qwen-tts:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test qwen-tts
run: |
make --jobs=5 --output-sync=target -C backend/python/qwen-tts
make --jobs=5 --output-sync=target -C backend/python/qwen-tts test
# TODO: s2-pro model is too large to load on CPU-only CI runners — re-enable
# when we have GPU runners or a smaller test model.
# tests-fish-speech:
# runs-on: ubuntu-latest
# timeout-minutes: 45
# steps:
# - name: Clone
# uses: actions/checkout@v6
# with:
# submodules: true
# - name: Dependencies
# run: |
# sudo apt-get update
# sudo apt-get install -y build-essential ffmpeg portaudio19-dev
# sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# # Install UV
# curl -LsSf https://astral.sh/uv/install.sh | sh
# pip install --user --no-cache-dir grpcio-tools==1.64.1
# - name: Test fish-speech
# run: |
# make --jobs=5 --output-sync=target -C backend/python/fish-speech
# make --jobs=5 --output-sync=target -C backend/python/fish-speech test
tests-qwen-asr:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg sox
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test qwen-asr
run: |
make --jobs=5 --output-sync=target -C backend/python/qwen-asr
make --jobs=5 --output-sync=target -C backend/python/qwen-asr test
tests-nemo:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential ffmpeg sox
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test nemo
run: |
make --jobs=5 --output-sync=target -C backend/python/nemo
make --jobs=5 --output-sync=target -C backend/python/nemo test
tests-voxcpm:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential ffmpeg
sudo apt-get install -y ca-certificates cmake curl patch python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Test voxcpm
run: |
make --jobs=5 --output-sync=target -C backend/python/voxcpm
make --jobs=5 --output-sync=target -C backend/python/voxcpm test
tests-llama-cpp-quantization:
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential cmake curl git python3-pip
# Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh
pip install --user --no-cache-dir grpcio-tools==1.64.1
- name: Build llama-quantize from llama.cpp
run: |
git clone --depth 1 https://github.com/ggml-org/llama.cpp.git /tmp/llama.cpp
cmake -B /tmp/llama.cpp/build -S /tmp/llama.cpp -DGGML_NATIVE=OFF
cmake --build /tmp/llama.cpp/build --target llama-quantize -j$(nproc)
sudo cp /tmp/llama.cpp/build/bin/llama-quantize /usr/local/bin/
- name: Install backend
run: |
make --jobs=5 --output-sync=target -C backend/python/llama-cpp-quantization
- name: Test llama-cpp-quantization
run: |
make --jobs=5 --output-sync=target -C backend/python/llama-cpp-quantization test
tests-acestep-cpp:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential cmake curl libopenblas-dev ffmpeg
- name: Setup Go
uses: actions/setup-go@v5
- name: Display Go version
run: go version
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Build acestep-cpp
run: |
make --jobs=5 --output-sync=target -C backend/go/acestep-cpp
- name: Test acestep-cpp
run: |
make --jobs=5 --output-sync=target -C backend/go/acestep-cpp test
tests-voxtral:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential cmake curl libopenblas-dev ffmpeg
- name: Setup Go
uses: actions/setup-go@v5
# You can test your matrix by printing the current Go version
- name: Display Go version
run: go version
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Build voxtral
run: |
make --jobs=5 --output-sync=target -C backend/go/voxtral
- name: Test voxtral
run: |
make --jobs=5 --output-sync=target -C backend/go/voxtral test
tests-e2e matrix .github/workflows/tests-e2e.yml
View raw YAML
---
name: 'E2E Backend Tests'
on:
pull_request:
push:
branches:
- master
tags:
- '*'
concurrency:
group: ci-tests-e2e-backend-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
tests-e2e-backend:
runs-on: ubuntu-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: ${{ matrix.go-version }}
cache: false
- name: Display Go version
run: go version
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential libopus-dev
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: '22'
- name: Build React UI
run: make react-ui
- name: Test Backend E2E
run: |
PATH="$PATH:$HOME/go/bin" make build-mock-backend test-e2e
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3.23
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
tests-ui-e2e matrix .github/workflows/tests-ui-e2e.yml
View raw YAML
---
name: 'UI E2E Tests'
on:
pull_request:
paths:
- 'core/http/**'
- 'tests/e2e-ui/**'
- 'tests/e2e/mock-backend/**'
push:
branches:
- master
concurrency:
group: ci-tests-ui-e2e-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
tests-ui-e2e:
runs-on: ubuntu-latest
strategy:
matrix:
go-version: ['1.26.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: ${{ matrix.go-version }}
cache: false
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: '22'
- name: Proto Dependencies
run: |
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
- name: System Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential libopus-dev
- name: Build UI test server
run: PATH="$PATH:$HOME/go/bin" make build-ui-test-server
- name: Install Playwright
working-directory: core/http/react-ui
run: |
npm install
npx playwright install --with-deps chromium
- name: Run Playwright tests
working-directory: core/http/react-ui
run: npx playwright test
- name: Upload Playwright report
if: ${{ failure() }}
uses: actions/upload-artifact@v7
with:
name: playwright-report
path: core/http/react-ui/playwright-report/
retention-days: 7
- name: Setup tmate session if tests fail
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3.23
with:
detached: true
connect-timeout-seconds: 180
limit-access-to-actor: true
update_swagger .github/workflows/update_swagger.yaml
View raw YAML
name: Update swagger
on:
schedule:
- cron: 0 20 * * *
workflow_dispatch:
jobs:
swagger:
if: github.repository == 'mudler/LocalAI'
strategy:
fail-fast: false
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: actions/setup-go@v5
with:
go-version: 'stable'
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install protobuf-compiler
- run: |
go install github.com/swaggo/swag/cmd/swag@latest
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
- name: Bump swagger 🔧
run: |
make protogen-go swagger
- name: Create Pull Request
uses: peter-evans/create-pull-request@v8
with:
token: ${{ secrets.UPDATE_BOT_TOKEN }}
push-to-fork: ci-forks/LocalAI
commit-message: 'feat(swagger): update swagger'
title: 'feat(swagger): update swagger'
branch: "update/swagger"
body: Update swagger
signoff: true
yaml-check .github/workflows/yaml-check.yml
View raw YAML
name: 'Yamllint GitHub Actions'
on:
- pull_request
jobs:
yamllint:
name: 'Yamllint'
runs-on: ubuntu-latest
steps:
- name: 'Checkout'
uses: actions/checkout@master
- name: 'Yamllint model gallery'
uses: karancode/yamllint-github-action@master
with:
yamllint_file_or_dir: 'gallery'
yamllint_strict: false
yamllint_comment: true
env:
GITHUB_ACCESS_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: 'Yamllint Backend gallery'
uses: karancode/yamllint-github-action@master
with:
yamllint_file_or_dir: 'backend'
yamllint_strict: false
yamllint_comment: true
env:
GITHUB_ACCESS_TOKEN: ${{ secrets.GITHUB_TOKEN }}