LocalAI/.github/workflows/image-pr.yml
Ettore Di Giacinto 5d1018495f
feat(intel): add diffusers/transformers support (#1746)
* feat(intel): add diffusers support

* try to consume upstream container image

* Debug

* Manually install deps

* Map transformers/hf cache dir to modelpath if not specified

* fix(compel): update initialization, pass by all gRPC options

* fix: add dependencies, implement transformers for xpu

* base it from the oneapi image

* Add pillow

* set threads if specified when launching the API

* Skip conda install if intel

* defaults to non-intel

* ci: add to pipelines

* prepare compel only if enabled

* Skip conda install if intel

* fix cleanup

* Disable compel by default

* Install torch 2.1.0 with Intel

* Skip conda on some setups

* Detect python

* Quiet output

* Do not override system python with conda

* Prefer python3

* Fixups

* exllama2: do not install without conda (overrides pytorch version)

* exllama/exllama2: do not install if not using cuda

* Add missing dataset dependency

* Small fixups, symlink to python, add requirements

* Add neural_speed to the deps

* correctly handle model offloading

* fix: device_map == xpu

* go back at calling python, fixed at dockerfile level

* Exllama2 restricted to only nvidia gpus

* Tokenizer to xpu
2024-03-07 14:37:45 +01:00

116 lines
No EOL
4.1 KiB
YAML

---
name: 'build container images tests'
on:
pull_request:
concurrency:
group: ci-${{ github.head_ref || github.ref }}-${{ github.repository }}
cancel-in-progress: true
jobs:
extras-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 }}
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' && 2 || 4 }}
matrix:
include:
- 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"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "1"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-cublas-cuda12-ffmpeg'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
base-image: "ubuntu:22.04"
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-hipblas'
ffmpeg: 'false'
image-type: 'extras'
base-image: "rocm/dev-ubuntu-22.04:6.0-complete"
runs-on: 'arc-runner-set'
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
tag-suffix: 'sycl-f16-ffmpeg'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
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 }}
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"
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04"
tag-suffix: 'sycl-f16-ffmpeg-core'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "1"
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"