mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-01 23:21:13 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix(ci): better handling of latest images for backends (#5735)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-06-27 10:32:58 +02:00
committed by GitHub
parent 6a650e68cb
commit cfc9dfa3d5
2 changed files with 3 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
.github/workflows/backend.yml vendored
View File

@@ -26,7 +26,6 @@ jobs:
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
backend: ${{ matrix.backend }}
latest-image: ${{ matrix.latest-image }}
dockerfile: $${ matrix.dockerfile }}
context: $${ matrix.context }}
secrets:
@@ -49,7 +48,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-11-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -61,7 +59,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-11-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -73,7 +70,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-11-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -85,7 +81,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-11-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 11 additional backends
@@ -98,7 +93,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-11-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -110,7 +104,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-11-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -122,7 +115,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-11-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -134,7 +126,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-11-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -146,7 +137,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-11-chatterbox'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 12 builds
@@ -159,7 +149,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-12-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -171,7 +160,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-12-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -183,7 +171,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-12-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -194,8 +181,7 @@ jobs:
tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-12-diffusers'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 12 additional backends
@@ -208,7 +194,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-12-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -220,7 +205,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-12-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -232,7 +216,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-12-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -244,7 +227,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-12-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
@@ -256,7 +238,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-12-chatterbox'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# hipblas builds
@@ -269,7 +250,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "rerankers"
latest-image: 'latest-gpu-rocm-hipblas-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -281,7 +261,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "vllm"
latest-image: 'latest-gpu-rocm-hipblas-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -293,7 +272,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "transformers"
latest-image: 'latest-gpu-rocm-hipblas-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -305,7 +283,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "diffusers"
latest-image: 'latest-gpu-rocm-hipblas-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# ROCm additional backends
@@ -318,7 +295,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "kokoro"
latest-image: 'latest-gpu-rocm-hipblas-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -330,7 +306,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "faster-whisper"
latest-image: 'latest-gpu-rocm-hipblas-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -342,7 +317,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "coqui"
latest-image: 'latest-gpu-rocm-hipblas-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
@@ -354,7 +328,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "bark"
latest-image: 'latest-gpu-rocm-hipblas-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# sycl builds
@@ -367,7 +340,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f32-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -379,7 +351,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f16-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -391,7 +362,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f32-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -403,7 +373,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f16-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -415,7 +384,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f32-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -427,7 +395,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f16-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -439,7 +406,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "diffusers"
latest-image: 'latest-gpu-intel-sycl-f32-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# SYCL additional backends
@@ -452,7 +418,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f32-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -464,7 +429,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f16-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -476,7 +440,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f32-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -488,7 +451,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f16-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -500,7 +462,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f32-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -512,7 +473,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f16-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
@@ -524,7 +484,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f32-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
@@ -536,7 +495,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f16-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# bark-cpp
@@ -549,6 +507,5 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-bark-cpp'
dockerfile: "./backend/Dockerfile.go"
context: "./"

20
.github/workflows/backend_build.yml vendored
View File

@@ -28,10 +28,6 @@ on:
description: 'Tag latest'
default: ''
type: string
latest-image:
description: 'Tag latest'
default: ''
type: string
tag-suffix:
description: 'Tag suffix'
default: ''
@@ -153,7 +149,7 @@ jobs:
type=sha
flavor: |
latest=${{ inputs.tag-latest }}
suffix=${{ inputs.tag-suffix }}
suffix=${{ inputs.tag-suffix }},onlatest=true
- name: Docker meta for PR
id: meta_pull_request
@@ -168,7 +164,7 @@ jobs:
type=sha,suffix=${{ 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 }}
suffix=${{ inputs.tag-suffix }},onlatest=true
## End testing image
- name: Set up QEMU
uses: docker/setup-qemu-action@master
@@ -210,7 +206,6 @@ jobs:
cache-from: type=gha
platforms: ${{ inputs.platforms }}
push: ${{ github.event_name != 'pull_request' }}
load: ${{ github.event_name != 'pull_request' && inputs.latest-image != '' && github.ref_type == 'tag' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
@@ -233,18 +228,7 @@ jobs:
tags: ${{ steps.meta_pull_request.outputs.tags }}
labels: ${{ steps.meta_pull_request.outputs.labels }}
- name: Cleanup
run: |
docker builder prune -f
docker system prune --force --volumes --all
- name: Latest tag
if: github.event_name != 'pull_request' && inputs.latest-image != '' && github.ref_type == 'tag'
run: |
docker tag localai/localai-backends:${{ steps.meta.outputs.version }} localai/localai-backends:${{ inputs.latest-image }}
docker push localai/localai-backends:${{ inputs.latest-image }}
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: |