mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-20 17:54:59 +00:00
feat: Add backend gallery (#5607)
* 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
GitHub
parent
a7a6020328
commit
2d64269763
114 changed files with 3996 additions and 1382 deletions
158
.github/workflows/image.yml
vendored
158
.github/workflows/image.yml
vendored
|
|
@ -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:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue