dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-17 00:05:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 15

feat: Add backend gallery (#5607)

Browse source 
* feat: Add backend gallery

This PR add support to manage backends as similar to models. There is
now available a backend gallery which can be used to install and remove
extra backends.
The backend gallery can be configured similarly as a model gallery, and
API calls allows to install and remove new backends in runtime, and as
well during the startup phase of LocalAI.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add backends docs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* wip: Backend Dockerfile for python backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat: drop extras images, build python backends separately

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixup on all backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Tweaks

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop old backends leftovers

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixup CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Move dockerfile upper

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix proto

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Feature dropped for consistency - we prefer model galleries

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add missing packages in the build image

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* exllama is ponly available on cublas

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* pin torch on chatterbox

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups to index

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Debug CI

* Install accellerators deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add target arch

* Add cuda minor version

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use self-hosted runners

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: use quay for test images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups for vllm and chatterbox

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups on CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chatterbox is only available for nvidia

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify CI builds

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt test, use qwen3

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(model gallery): add jina-reranker-v1-tiny-en-gguf

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use reranker from llama.cpp in AIO images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Limit concurrent jobs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto 2025-06-15 14:56:52 +02:00 • committed by GitHub
parent a7a6020328
commit 2d64269763
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
114 changed files with 3996 additions and 1382 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.github/dependabot.yml vendored
View file

@ -61,10 +61,6 @@ updates:
directory: "/backend/python/openvoice"
schedule:
interval: "weekly"
- package-ecosystem: "pip"
directory: "/backend/python/parler-tts"
schedule:
interval: "weekly"
- package-ecosystem: "pip"
directory: "/backend/python/rerankers"
schedule:

85
.github/workflows/image-pr.yml vendored
View file

@ -9,13 +9,12 @@ concurrency:
cancel-in-progress: true
jobs:
extras-image-build:
image-build:
uses: ./.github/workflows/image_build.yml
with:
tag-latest: ${{ matrix.tag-latest }}
tag-suffix: ${{ matrix.tag-suffix }}
ffmpeg: ${{ matrix.ffmpeg }}
image-type: ${{ matrix.image-type }}
build-type: ${{ matrix.build-type }}
cuda-major-version: ${{ matrix.cuda-major-version }}
cuda-minor-version: ${{ matrix.cuda-minor-version }}
@ -36,16 +35,6 @@ jobs:
fail-fast: false
matrix:
include:
# This is basically covered by the AIO test
# - build-type: ''
# platforms: 'linux/amd64'
# tag-latest: 'false'
# tag-suffix: '-ffmpeg'
# ffmpeg: 'true'
# image-type: 'extras'
# runs-on: 'arc-runner-set'
# base-image: "ubuntu:22.04"
# makeflags: "--jobs=3 --output-sync=target"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
@ -53,8 +42,7 @@ jobs:
tag-latest: 'false'
tag-suffix: '-cublas-cuda12-ffmpeg'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'hipblas'
@ -62,10 +50,9 @@ jobs:
tag-latest: 'false'
tag-suffix: '-hipblas'
ffmpeg: 'false'
image-type: 'extras'
base-image: "rocm/dev-ubuntu-22.04:6.1"
grpc-base-image: "ubuntu:22.04"
runs-on: 'arc-runner-set'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
@ -74,77 +61,13 @@ jobs:
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16-ffmpeg'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
runs-on: 'ubuntu-latest'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'vulkan'
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-vulkan-ffmpeg-core'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
makeflags: "--jobs=4 --output-sync=target"
# core-image-build:
# uses: ./.github/workflows/image_build.yml
# with:
# tag-latest: ${{ matrix.tag-latest }}
# tag-suffix: ${{ matrix.tag-suffix }}
# ffmpeg: ${{ matrix.ffmpeg }}
# image-type: ${{ matrix.image-type }}
# 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 }}
# secrets:
# dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
# dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
# quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
# quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
# strategy:
# matrix:
# include:
# - build-type: ''
# platforms: 'linux/amd64'
# tag-latest: 'false'
# tag-suffix: '-ffmpeg-core'
# ffmpeg: 'true'
# image-type: 'core'
# runs-on: 'ubuntu-latest'
# base-image: "ubuntu:22.04"
# makeflags: "--jobs=4 --output-sync=target"
# - build-type: 'sycl_f16'
# platforms: 'linux/amd64'
# tag-latest: 'false'
# base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
# grpc-base-image: "ubuntu:22.04"
# tag-suffix: 'sycl-f16-ffmpeg-core'
# ffmpeg: 'true'
# image-type: 'core'
# runs-on: 'arc-runner-set'
# makeflags: "--jobs=3 --output-sync=target"
# - build-type: 'cublas'
# cuda-major-version: "12"
# cuda-minor-version: "0"
# platforms: 'linux/amd64'
# tag-latest: 'false'
# tag-suffix: '-cublas-cuda12-ffmpeg-core'
# ffmpeg: 'true'
# image-type: 'core'
# runs-on: 'ubuntu-latest'
# base-image: "ubuntu:22.04"
# makeflags: "--jobs=4 --output-sync=target"
# - build-type: 'vulkan'
# platforms: 'linux/amd64'
# tag-latest: 'false'
# tag-suffix: '-vulkan-ffmpeg-core'
# ffmpeg: 'true'
# image-type: 'core'
# runs-on: 'ubuntu-latest'
# base-image: "ubuntu:22.04"
# makeflags: "--jobs=4 --output-sync=target"

158
.github/workflows/image.yml vendored
View file

@ -37,24 +37,9 @@ jobs:
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: 2
matrix:
include:
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-hipblas-extras'
ffmpeg: 'true'
image-type: 'extras'
aio: "-aio-gpu-hipblas"
base-image: "rocm/dev-ubuntu-22.04:6.1"
grpc-base-image: "ubuntu:22.04"
latest-image: 'latest-gpu-hipblas-extras'
latest-image-aio: 'latest-aio-gpu-hipblas'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'false'
@ -66,112 +51,8 @@ jobs:
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
latest-image: 'latest-gpu-hipblas'
self-hosted-jobs:
uses: ./.github/workflows/image_build.yml
with:
tag-latest: ${{ matrix.tag-latest }}
tag-suffix: ${{ matrix.tag-suffix }}
ffmpeg: ${{ matrix.ffmpeg }}
image-type: ${{ matrix.image-type }}
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 }}
aio: ${{ matrix.aio }}
makeflags: ${{ matrix.makeflags }}
latest-image: ${{ matrix.latest-image }}
latest-image-aio: ${{ matrix.latest-image-aio }}
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' && 5 || 8 }}
matrix:
include:
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-cublas-cuda11-extras'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
aio: "-aio-gpu-nvidia-cuda-11"
latest-image: 'latest-gpu-nvidia-cuda-11-extras'
latest-image-aio: 'latest-aio-gpu-nvidia-cuda-11'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-cublas-cuda12-extras'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
aio: "-aio-gpu-nvidia-cuda-12"
latest-image: 'latest-gpu-nvidia-cuda-12-extras'
latest-image-aio: 'latest-aio-gpu-nvidia-cuda-12'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16-extras'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
aio: "-aio-gpu-intel-f16"
latest-image: 'latest-gpu-intel-f16-extras'
latest-image-aio: 'latest-aio-gpu-intel-f16'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32-extras'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
aio: "-aio-gpu-intel-f32"
latest-image: 'latest-gpu-intel-f32-extras'
latest-image-aio: 'latest-aio-gpu-intel-f32'
makeflags: "--jobs=3 --output-sync=target"
# Core images
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
latest-image: 'latest-gpu-intel-f16'
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
latest-image: 'latest-gpu-intel-f32'
aio: "-aio-gpu-hipblas"
latest-image-aio: 'latest-aio-gpu-hipblas'
core-image-build:
uses: ./.github/workflows/image_build.yml
@ -226,7 +107,9 @@ jobs:
base-image: "ubuntu:22.04"
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'false'
latest-image: 'latest-gpu-nvidia-cuda-12'
latest-image: 'latest-gpu-nvidia-cuda-11'
aio: "-aio-gpu-nvidia-cuda-11"
latest-image-aio: 'latest-aio-gpu-nvidia-cuda-11'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
@ -240,6 +123,8 @@ jobs:
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
latest-image: 'latest-gpu-nvidia-cuda-12'
aio: "-aio-gpu-nvidia-cuda-12"
latest-image-aio: 'latest-aio-gpu-nvidia-cuda-12'
- build-type: 'vulkan'
platforms: 'linux/amd64'
tag-latest: 'false'
@ -251,6 +136,35 @@ jobs:
skip-drivers: 'false'
makeflags: "--jobs=4 --output-sync=target"
latest-image: 'latest-gpu-vulkan'
aio: "-aio-gpu-vulkan"
latest-image-aio: 'latest-aio-gpu-vulkan'
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f16'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
latest-image: 'latest-gpu-intel-f16'
aio: "-aio-gpu-intel-f16"
latest-image-aio: 'latest-aio-gpu-intel-f16'
- build-type: 'sycl_f32'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
grpc-base-image: "ubuntu:22.04"
tag-suffix: '-sycl-f32'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
latest-image: 'latest-gpu-intel-f32'
aio: "-aio-gpu-intel-f32"
latest-image-aio: 'latest-aio-gpu-intel-f32'
gh-runner:
uses: ./.github/workflows/image_build.yml
with:

20
.github/workflows/image_build.yml vendored
View file

@ -53,10 +53,6 @@ on:
description: 'Skip drivers by default'
default: 'false'
type: string
image-type:
description: 'Image type'
default: ''
type: string
runs-on:
description: 'Runs on'
required: true
@ -159,11 +155,11 @@ jobs:
uses: docker/metadata-action@v5
with:
images: |
ttl.sh/localai-ci-pr-${{ github.event.number }}
quay.io/go-skynet/ci-tests
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
type=ref,event=branch,suffix=localai${{ 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 }}
@ -211,7 +207,7 @@ jobs:
password: ${{ secrets.dockerPassword }}
- name: Login to DockerHub
if: github.event_name != 'pull_request'
# if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: quay.io
@ -232,7 +228,6 @@ jobs:
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
FFMPEG=${{ inputs.ffmpeg }}
IMAGE_TYPE=${{ inputs.image-type }}
BASE_IMAGE=${{ inputs.base-image }}
GRPC_BASE_IMAGE=${{ inputs.grpc-base-image || inputs.base-image }}
GRPC_MAKEFLAGS=--jobs=4 --output-sync=target
@ -261,7 +256,6 @@ jobs:
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
FFMPEG=${{ inputs.ffmpeg }}
IMAGE_TYPE=${{ inputs.image-type }}
BASE_IMAGE=${{ inputs.base-image }}
GRPC_BASE_IMAGE=${{ inputs.grpc-base-image || inputs.base-image }}
GRPC_MAKEFLAGS=--jobs=4 --output-sync=target
@ -275,10 +269,6 @@ jobs:
push: true
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
- name: Testing image
if: github.event_name == 'pull_request'
run: |
echo "Image is available at ttl.sh/localai-ci-pr-${{ github.event.number }}:${{ steps.meta_pull_request.outputs.version }}" >> $GITHUB_STEP_SUMMARY
## End testing image
- name: Build and push AIO image
if: inputs.aio != ''

457
.github/workflows/python_backend.yml vendored Normal file
View file

@ -0,0 +1,457 @@
---
name: 'build python backend container images'
on:
push:
branches:
- master
tags:
- '*'
pull_request:
concurrency:
group: ci-backends-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
backend-jobs:
uses: ./.github/workflows/python_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 }}
latest-image: ${{ matrix.latest-image }}
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:
# CUDA 11 builds
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-rerankers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-11-rerankers'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-vllm'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-11-vllm'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-transformers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-11-transformers'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-diffusers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-11-diffusers'
# CUDA 11 additional backends
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-kokoro'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-11-kokoro'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-faster-whisper'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-11-faster-whisper'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-coqui'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-11-coqui'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-bark'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-11-bark'
- build-type: 'cublas'
cuda-major-version: "11"
cuda-minor-version: "7"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-11-chatterbox'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-11-chatterbox'
# CUDA 12 builds
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-rerankers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-12-rerankers'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-vllm'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-12-vllm'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-transformers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-12-transformers'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-12-diffusers'
# CUDA 12 additional backends
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-kokoro'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-12-kokoro'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-faster-whisper'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-12-faster-whisper'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-coqui'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-12-coqui'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-bark'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-12-bark'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-nvidia-cuda-12-chatterbox'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-12-chatterbox'
# hipblas builds
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-rerankers'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "rerankers"
latest-image: 'latest-gpu-rocm-hipblas-rerankers'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-vllm'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "vllm"
latest-image: 'latest-gpu-rocm-hipblas-vllm'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-transformers'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "transformers"
latest-image: 'latest-gpu-rocm-hipblas-transformers'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-diffusers'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "diffusers"
latest-image: 'latest-gpu-rocm-hipblas-diffusers'
# ROCm additional backends
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-kokoro'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "kokoro"
latest-image: 'latest-gpu-rocm-hipblas-kokoro'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-faster-whisper'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "faster-whisper"
latest-image: 'latest-gpu-rocm-hipblas-faster-whisper'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-coqui'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "coqui"
latest-image: 'latest-gpu-rocm-hipblas-coqui'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-rocm-hipblas-bark'
runs-on: 'arc-runner-set'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "bark"
latest-image: 'latest-gpu-rocm-hipblas-bark'
# sycl builds
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-rerankers'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f32-rerankers'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-rerankers'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f16-rerankers'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-vllm'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f32-vllm'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-vllm'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f16-vllm'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-transformers'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f32-transformers'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-transformers'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f16-transformers'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-diffusers'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "diffusers"
latest-image: 'latest-gpu-intel-sycl-f32-diffusers'
# SYCL additional backends
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-kokoro'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f32-kokoro'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-kokoro'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f16-kokoro'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-faster-whisper'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f32-faster-whisper'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-faster-whisper'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f16-faster-whisper'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-coqui'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f32-coqui'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-coqui'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f16-coqui'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f32-bark'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f32-bark'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'true'
tag-suffix: '-gpu-intel-sycl-f16-bark'
runs-on: 'arc-runner-set'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f16-bark'

198
.github/workflows/python_backend_build.yml vendored Normal file
View file

@ -0,0 +1,198 @@
---
name: 'build python backend container images (reusable)'
on:
workflow_call:
inputs:
base-image:
description: 'Base image'
required: true
type: string
build-type:
description: 'Build type'
default: ''
type: string
cuda-major-version:
description: 'CUDA major version'
default: "12"
type: string
cuda-minor-version:
description: 'CUDA minor version'
default: "1"
type: string
platforms:
description: 'Platforms'
default: ''
type: string
tag-latest:
description: 'Tag latest'
default: ''
type: string
latest-image:
description: 'Tag latest'
default: ''
type: string
tag-suffix:
description: 'Tag suffix'
default: ''
type: string
runs-on:
description: 'Runs on'
required: true
default: ''
type: string
backend:
description: 'Backend to build'
required: true
type: string
secrets:
dockerUsername:
required: true
dockerPassword:
required: true
quayUsername:
required: true
quayPassword:
required: true
jobs:
reusable_python_backend-build:
runs-on: ${{ inputs.runs-on }}
steps:
- name: Force Install GIT latest
run: |
sudo apt-get update \
&& sudo apt-get install -y software-properties-common \
&& sudo apt-get update \
&& sudo add-apt-repository -y ppa:git-core/ppa \
&& sudo apt-get update \
&& sudo apt-get install -y git
- name: Checkout
uses: actions/checkout@v4
- name: Release space from worker
if: inputs.runs-on == 'ubuntu-latest'
run: |
echo "Listing top largest packages"
pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
head -n 30 <<< "${pkgs}"
echo
df -h
echo
sudo apt-get autoremove -y
sudo apt-get clean
echo
df -h
- name: Docker meta
id: meta
if: github.event_name != 'pull_request'
uses: docker/metadata-action@v5
with:
images: |
quay.io/go-skynet/local-ai-backends
localai/localai-backends
tags: |
type=ref,event=branch
type=semver,pattern={{raw}}
type=sha
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
- name: Docker meta for PR
id: meta_pull_request
if: github.event_name == 'pull_request'
uses: docker/metadata-action@v5
with:
images: |
quay.io/go-skynet/ci-tests
tags: |
type=ref,event=branch,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=semver,pattern={{raw}},suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
type=sha,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
## End testing image
- name: Set up QEMU
uses: docker/setup-qemu-action@master
with:
platforms: all
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@master
- name: Login to DockerHub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.dockerUsername }}
password: ${{ secrets.dockerPassword }}
- name: Login to Quay.io
# if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: quay.io
username: ${{ secrets.quayUsername }}
password: ${{ secrets.quayPassword }}
- name: Build and push
uses: docker/build-push-action@v6
if: github.event_name != 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
context: ./backend
file: ./backend/Dockerfile.python
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
- name: Build and push (PR)
uses: docker/build-push-action@v6
if: github.event_name == 'pull_request'
with:
builder: ${{ steps.buildx.outputs.name }}
build-args: |
BUILD_TYPE=${{ inputs.build-type }}
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
BASE_IMAGE=${{ inputs.base-image }}
BACKEND=${{ inputs.backend }}
context: ./backend
file: ./backend/Dockerfile.python
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: true
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
- name: Cleanup
run: |
docker builder prune -f
docker system prune --force --volumes --all
- name: Latest tag
if: github.event_name != 'pull_request' && inputs.latest-image != '' && github.ref_type == 'tag'
run: |
docker pull localai/localai-backends:${{ steps.meta.outputs.version }}
docker tag localai/localai-backends:${{ steps.meta.outputs.version }} localai/localai-backends:${{ inputs.latest-image }}
docker push localai/localai-backends:${{ inputs.latest-image }}
docker pull quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }}
docker tag quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }} quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
docker push quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
- name: job summary
run: |
echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY

2
.github/workflows/test.yml vendored
View file

@ -188,7 +188,7 @@ jobs:
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Build images
run: |
docker build --build-arg FFMPEG=true --build-arg IMAGE_TYPE=extras --build-arg EXTRA_BACKENDS=rerankers --build-arg MAKEFLAGS="--jobs=5 --output-sync=target" -t local-ai:tests -f Dockerfile .
docker build --build-arg FFMPEG=true --build-arg MAKEFLAGS="--jobs=5 --output-sync=target" -t local-ai:tests -f Dockerfile .
BASE_IMAGE=local-ai:tests DOCKER_AIO_IMAGE=local-ai-aio:test make docker-aio
- name: Test
run: |