mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-11 16:57:40 -04:00
fix(backend gallery): intel images for python-based backends, re-add exllama2 (#5928)
chore(backend gallery): fix intel images for python-based backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
committed by
GitHub
GitHub
parent
d25145e641
commit
36179ffbed
177
.github/workflows/backend.yml
vendored
177
.github/workflows/backend.yml
vendored
@@ -381,24 +381,12 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
# sycl builds
|
||||
- build-type: 'sycl_f32'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-rerankers'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "rerankers"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-rerankers'
|
||||
tag-suffix: '-gpu-intel-rerankers'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
@@ -429,60 +417,36 @@ jobs:
|
||||
backend: "llama-cpp"
|
||||
dockerfile: "./backend/Dockerfile.llama-cpp"
|
||||
context: "./"
|
||||
- build-type: 'sycl_f32'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-vllm'
|
||||
tag-suffix: '-gpu-intel-vllm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "vllm"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-vllm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "vllm"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-transformers'
|
||||
tag-suffix: '-gpu-intel-transformers'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "transformers"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-transformers'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "transformers"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-diffusers'
|
||||
tag-suffix: '-gpu-intel-diffusers'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
@@ -490,96 +454,48 @@ jobs:
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
# SYCL additional backends
|
||||
- build-type: 'sycl_f32'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-kokoro'
|
||||
tag-suffix: '-gpu-intel-kokoro'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "kokoro"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-kokoro'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "kokoro"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-faster-whisper'
|
||||
tag-suffix: '-gpu-intel-faster-whisper'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "faster-whisper"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-faster-whisper'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "faster-whisper"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-coqui'
|
||||
tag-suffix: '-gpu-intel-coqui'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "coqui"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-coqui'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "coqui"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f32-bark'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "bark"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'sycl_f16'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-sycl-f16-bark'
|
||||
tag-suffix: '-gpu-intel-bark'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
@@ -930,6 +846,67 @@ jobs:
|
||||
backend: "rfdetr"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
# exllama2
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-exllama2'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "exllama2"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "0"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-12-exllama2'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "exllama2"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "11"
|
||||
cuda-minor-version: "7"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-11-exllama2'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:22.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "exllama2"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'intel'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-intel-exllama2'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
|
||||
skip-drivers: 'false'
|
||||
backend: "exllama2"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
- build-type: 'hipblas'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
skip-drivers: 'true'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-hipblas-exllama2'
|
||||
base-image: "rocm/dev-ubuntu-22.04:6.1"
|
||||
runs-on: 'ubuntu-latest'
|
||||
backend: "exllama2"
|
||||
dockerfile: "./backend/Dockerfile.python"
|
||||
context: "./backend"
|
||||
# runs out of space on the runner
|
||||
# - build-type: 'hipblas'
|
||||
# cuda-major-version: ""
|
||||
|
||||
Reference in New Issue
Block a user