Skip to content

feat(llama.cpp): add distributed llama.cpp inferencing #2064

feat(llama.cpp): add distributed llama.cpp inferencing

feat(llama.cpp): add distributed llama.cpp inferencing #2064

Workflow file for this run

---
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 }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
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"
makeflags: "--jobs=3 --output-sync=target"
- 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"
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'hipblas'
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-hipblas'
ffmpeg: 'false'
image-type: 'extras'
base-image: "rocm/dev-ubuntu-22.04:6.1"
grpc-base-image: "ubuntu:22.04"
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16-ffmpeg'
ffmpeg: 'true'
image-type: 'extras'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
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 }}
grpc-base-image: ${{ matrix.grpc-base-image }}
makeflags: ${{ matrix.makeflags }}
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"
makeflags: "--jobs=4 --output-sync=target"
- build-type: 'sycl_f16'
platforms: 'linux/amd64'
tag-latest: 'false'
base-image: "intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04"
grpc-base-image: "ubuntu:22.04"
tag-suffix: 'sycl-f16-ffmpeg-core'
ffmpeg: 'true'
image-type: 'core'
runs-on: 'arc-runner-set'
makeflags: "--jobs=3 --output-sync=target"
- 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"
makeflags: "--jobs=4 --output-sync=target"