mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-19 14:17:21 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: package GPU libraries inside backend containers for unified base image (#7891)

Browse Source 
* Initial plan

* Add GPU library packaging for isolated backend environments

- Create scripts/build/package-gpu-libs.sh for packaging CUDA, ROCm, SYCL, and Vulkan libraries
- Update llama-cpp, whisper, stablediffusion-ggml package.sh to include GPU libraries
- Update Dockerfile.python to package GPU libraries into Python backends
- Update libbackend.sh to set LD_LIBRARY_PATH for GPU library loading

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

* Address code review feedback: fix variable consistency and quoting

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

* Fix code review issues: improve glob handling and remove redundant variable

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

* Simplify main Dockerfile and workflow to use unified base image

- Remove GPU-specific driver installation from Dockerfile (CUDA, ROCm, Vulkan, Intel)
- Simplify image.yml workflow to build single unified base image for linux/amd64 and linux/arm64
- GPU libraries are now packaged in individual backend containers

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Copilot
2026-01-07 15:48:51 +01:00
committed by GitHub
parent 7abc0242bb
commit fd53978a7b
8 changed files with 331 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
.github/workflows/image.yml vendored
View File

@@ -13,42 +13,7 @@ concurrency:
cancel-in-progress: true
jobs:
hipblas-jobs:
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 }}
aio: ${{ matrix.aio }}
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"
aio: "-aio-gpu-hipblas"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
# Unified base image build - GPU drivers are now packaged in individual backends
core-image-build:
uses: ./.github/workflows/image_build.yml
with:
@@ -72,9 +37,10 @@ jobs:
quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
strategy:
#max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
matrix:
include:
# Unified base image for all platforms
# GPU-specific backends will be pulled at runtime and contain their own GPU libraries
- build-type: ''
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
@@ -86,101 +52,3 @@ jobs:
skip-drivers: 'false'
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "9"
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"
aio: "-aio-gpu-nvidia-cuda-12"
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"
aio: "-aio-gpu-nvidia-cuda-13"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
- build-type: 'vulkan'
platforms: 'linux/amd64'
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"
aio: "-aio-gpu-vulkan"
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"
aio: "-aio-gpu-intel"
ubuntu-version: '2404'
ubuntu-codename: 'noble'
gh-runner:
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 }}
aio: ${{ matrix.aio }}
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: "9"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64'
base-image: "ubuntu:24.04"
runs-on: 'ubuntu-24.04-arm'
makeflags: "--jobs=4 --output-sync=target"
skip-drivers: 'true'
ubuntu-version: "2404"
ubuntu-codename: 'noble'
- 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'