mirror of
https://github.com/mudler/LocalAI.git
synced 2026-01-07 05:49:40 -05:00
e6ba26c3e7
* ci(workflows): bump GitHub Actions images to Ubuntu 24.04 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): remove CUDA 11.x support from GitHub Actions (incompatible with ubuntu:24.04) Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): bump GitHub Actions CUDA support to 12.9 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): bump base image to ubuntu:24.04 and adjust Vulkan SDK/packages Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix(backend): correct context paths for Python backends in workflows, Makefile and Dockerfile Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): disable parallel backend builds to avoid race conditions Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): export CUDA_MAJOR_VERSION and CUDA_MINOR_VERSION for override Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(backend): update backend Dockerfiles to Ubuntu 24.04 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(backend): add ROCm env vars and default AMDGPU_TARGETS for hipBLAS builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(chatterbox): bump ROCm PyTorch to 2.9.1+rocm6.4 and update index URL; align hipblas requirements Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore: add local-ai-launcher to .gitignore Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): fix backends GitHub Actions workflows after rebase Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): use build-time UBUNTU_VERSION variable Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(docker): remove libquadmath0 from requirements-stage base image Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): add backends/vllm to .NOTPARALLEL to prevent parallel builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix(docker): correct CUDA installation steps in backend Dockerfiles Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(backend): update ROCm to 6.4 and align Python hipblas requirements Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): switch GitHub Actions runners to Ubuntu-24.04 for CUDA on arm64 builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): update base image and backend Dockerfiles for Ubuntu 24.04 compatibility on arm64 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(backend): increase timeout for uv installs behind slow networks on backend/Dockerfile.python Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): switch GitHub Actions runners to Ubuntu-24.04 for vibevoice backend Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): fix failing GitHub Actions runners Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix: Allow FROM_SOURCE to be unset, use upstream Intel images etc. Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(build): rm all traces of CUDA 11 Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(build): Add Ubuntu codename as an argument Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com>
30 lines
1.1 KiB
YAML
30 lines
1.1 KiB
YAML
services:
|
|
api:
|
|
# See https://localai.io/basics/getting_started/#container-images for
|
|
# a list of available container images (or build your own with the provided Dockerfile)
|
|
# Available images with CUDA, ROCm, SYCL
|
|
# Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
|
|
# Image list (dockerhub): https://hub.docker.com/r/localai/localai
|
|
image: quay.io/go-skynet/local-ai:master
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
- IMAGE_TYPE=core
|
|
- BASE_IMAGE=ubuntu:24.04
|
|
ports:
|
|
- 8080:8080
|
|
env_file:
|
|
- .env
|
|
environment:
|
|
- MODELS_PATH=/models
|
|
# - DEBUG=true
|
|
volumes:
|
|
- ./models:/models:cached
|
|
- ./images/:/tmp/generated/images/
|
|
command:
|
|
# Here we can specify a list of models to run (see quickstart https://localai.io/basics/getting_started/#running-models )
|
|
# or an URL pointing to a YAML configuration file, for example:
|
|
# - https://gist.githubusercontent.com/mudler/ad601a0488b497b69ec549150d9edd18/raw/a8a8869ef1bb7e3830bf5c0bae29a0cce991ff8d/phi-2.yaml
|
|
- phi-2
|