mirror of
https://github.com/mudler/LocalAI.git
synced 2026-01-15 15:09:39 -06:00
* 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>
46 lines
2.0 KiB
Bash
Executable File
46 lines
2.0 KiB
Bash
Executable File
#!/bin/bash
|
|
set -e
|
|
|
|
EXTRA_PIP_INSTALL_FLAGS="--no-build-isolation"
|
|
|
|
# Avoid to overcommit the CPU during build
|
|
# https://github.com/vllm-project/vllm/issues/20079
|
|
# https://docs.vllm.ai/en/v0.8.3/serving/env_vars.html
|
|
# https://docs.redhat.com/it/documentation/red_hat_ai_inference_server/3.0/html/vllm_server_arguments/environment_variables-server-arguments
|
|
export NVCC_THREADS=2
|
|
export MAX_JOBS=1
|
|
|
|
backend_dir=$(dirname $0)
|
|
|
|
if [ -d $backend_dir/common ]; then
|
|
source $backend_dir/common/libbackend.sh
|
|
else
|
|
source $backend_dir/../common/libbackend.sh
|
|
fi
|
|
|
|
# This is here because the Intel pip index is broken and returns 200 status codes for every package name, it just doesn't return any package links.
|
|
# This makes uv think that the package exists in the Intel pip index, and by default it stops looking at other pip indexes once it finds a match.
|
|
# We need uv to continue falling through to the pypi default index to find optimum[openvino] in the pypi index
|
|
# the --upgrade actually allows us to *downgrade* torch to the version provided in the Intel pip index
|
|
if [ "x${BUILD_PROFILE}" == "xintel" ]; then
|
|
EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
|
|
fi
|
|
|
|
# We don't embed this into the images as it is a large dependency and not always needed.
|
|
# Besides, the speed inference are not actually usable in the current state for production use-cases.
|
|
if [ "x${BUILD_TYPE}" == "x" ] && [ "x${FROM_SOURCE:-}" == "xtrue" ]; then
|
|
ensureVenv
|
|
# https://docs.vllm.ai/en/v0.6.1/getting_started/cpu-installation.html
|
|
if [ ! -d vllm ]; then
|
|
git clone https://github.com/vllm-project/vllm
|
|
fi
|
|
pushd vllm
|
|
uv pip install wheel packaging ninja "setuptools>=49.4.0" numpy typing-extensions pillow setuptools-scm grpcio==1.68.1 protobuf bitsandbytes
|
|
uv pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
|
|
VLLM_TARGET_DEVICE=cpu python setup.py install
|
|
popd
|
|
rm -rf vllm
|
|
else
|
|
installRequirements
|
|
fi
|