LocalAI/.github/workflows/python_backend.yml

---
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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            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: 'ubuntu-latest'
            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
            backend: "bark"
            latest-image: 'latest-gpu-intel-sycl-f16-bark'