dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-28 14:35:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 12

feat: Use ubuntu as base for container images, drop deprecated ggml-transformers backends (#1689)

Browse source 
* cleanup backends

* switch image to ubuntu 22.04

* adapt commands for ubuntu

* transformers cleanup

* no contrib on ubuntu

* Change test model to gguf

* ci: disable bark tests (too cpu-intensive)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* cleanup

* refinements

* use intel base image

* Makefile: Add docker targets

* Change test model

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-02-08 20:12:51 +01:00 • committed by GitHub
parent d0a6a35b55
commit ddd21f1644
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 161 additions and 466 deletions
Download patch file Download diff file Expand all files Collapse all files

29
Dockerfile
View file

@ -1,9 +1,11 @@
ARG GO_VERSION=1.21-bullseye
ARG GO_VERSION=1.21
ARG IMAGE_TYPE=extras
ARG BASE_IMAGE=ubuntu:22.04
# extras or core
FROM ${BASE_IMAGE} as requirements-core
FROM golang:$GO_VERSION as requirements-core
ARG GO_VERSION=1.21.7
ARG BUILD_TYPE
ARG CUDA_MAJOR_VERSION=11
ARG CUDA_MINOR_VERSION=7
@ -11,14 +13,17 @@ ARG TARGETARCH
ARG TARGETVARIANT
ENV BUILD_TYPE=${BUILD_TYPE}
ENV DEBIAN_FRONTEND=noninteractive
ENV EXTERNAL_GRPC_BACKENDS="coqui:/build/backend/python/coqui/run.sh,huggingface-embeddings:/build/backend/python/sentencetransformers/run.sh,petals:/build/backend/python/petals/run.sh,transformers:/build/backend/python/transformers/run.sh,sentencetransformers:/build/backend/python/sentencetransformers/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,exllama:/build/backend/python/exllama/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh,mamba:/build/backend/python/mamba/run.sh,exllama2:/build/backend/python/exllama2/run.sh,transformers-musicgen:/build/backend/python/transformers-musicgen/run.sh"
ARG GO_TAGS="stablediffusion tinydream tts"
RUN apt-get update && \
apt-get install -y ca-certificates curl patch pip cmake && apt-get clean
apt-get install -y ca-certificates curl patch pip cmake git && apt-get clean
# Install Go
RUN curl -L -s https://go.dev/dl/go$GO_VERSION.linux-$TARGETARCH.tar.gz | tar -v -C /usr/local -xz
ENV PATH $PATH:/usr/local/go/bin
COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
RUN update-ca-certificates
@ -30,21 +35,13 @@ RUN echo "Target Variant: $TARGETVARIANT"
# CuBLAS requirements
RUN if [ "${BUILD_TYPE}" = "cublas" ]; then \
apt-get install -y software-properties-common && \
apt-add-repository contrib && \
curl -O https://developer.download.nvidia.com/compute/cuda/repos/debian11/x86_64/cuda-keyring_1.0-1_all.deb && \
dpkg -i cuda-keyring_1.0-1_all.deb && \
rm -f cuda-keyring_1.0-1_all.deb && \
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb && \
dpkg -i cuda-keyring_1.1-1_all.deb && \
rm -f cuda-keyring_1.1-1_all.deb && \
apt-get update && \
apt-get install -y cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} && apt-get clean \
; fi
# oneapi requirements
RUN if [ "${BUILD_TYPE}" = "sycl_f16" ] || [ "${BUILD_TYPE}" = "sycl_f32" ]; then \
wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/163da6e4-56eb-4948-aba3-debcec61c064/l_BaseKit_p_2024.0.1.46_offline.sh && \
sh ./l_BaseKit_p_2024.0.1.46_offline.sh -a -s --eula accept && \
rm -rf l_BaseKit_p_2024.0.1.46_offline.sh \
; fi
ENV PATH /usr/local/cuda/bin:${PATH}
# OpenBLAS requirements and stable diffusion