mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-16 15:55:00 +00:00

* feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
123 lines
No EOL
4.2 KiB
Text
123 lines
No EOL
4.2 KiB
Text
ARG BASE_IMAGE=ubuntu:22.04
|
|
|
|
FROM ${BASE_IMAGE} AS builder
|
|
ARG BACKEND=rerankers
|
|
ARG BUILD_TYPE
|
|
ENV BUILD_TYPE=${BUILD_TYPE}
|
|
ARG CUDA_MAJOR_VERSION
|
|
ARG CUDA_MINOR_VERSION
|
|
ARG SKIP_DRIVERS=false
|
|
ENV CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION}
|
|
ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION}
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ARG TARGETARCH
|
|
ARG TARGETVARIANT
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
build-essential \
|
|
ccache \
|
|
ca-certificates \
|
|
espeak-ng \
|
|
curl \
|
|
libssl-dev \
|
|
git \
|
|
git-lfs \
|
|
unzip \
|
|
upx-ucl \
|
|
curl python3-pip \
|
|
python-is-python3 \
|
|
python3-dev llvm \
|
|
python3-venv make && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/* && \
|
|
pip install --upgrade pip
|
|
|
|
|
|
# Cuda
|
|
ENV PATH=/usr/local/cuda/bin:${PATH}
|
|
|
|
# HipBLAS requirements
|
|
ENV PATH=/opt/rocm/bin:${PATH}
|
|
|
|
# Vulkan requirements
|
|
RUN <<EOT bash
|
|
if [ "${BUILD_TYPE}" = "vulkan" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
software-properties-common pciutils wget gpg-agent && \
|
|
wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
|
|
wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
|
|
apt-get update && \
|
|
apt-get install -y \
|
|
vulkan-sdk && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
fi
|
|
EOT
|
|
|
|
# CuBLAS requirements
|
|
RUN <<EOT bash
|
|
if [ "${BUILD_TYPE}" = "cublas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
software-properties-common pciutils
|
|
if [ "amd64" = "$TARGETARCH" ]; then
|
|
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
|
|
fi
|
|
if [ "arm64" = "$TARGETARCH" ]; then
|
|
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb
|
|
fi
|
|
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 --no-install-recommends \
|
|
cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
|
libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
|
libcurand-dev-${CUDA_MAJOR_VERSION}-${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 && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
fi
|
|
EOT
|
|
|
|
# If we are building with clblas support, we need the libraries for the builds
|
|
RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
libclblast-dev && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/* \
|
|
; fi
|
|
|
|
RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
hipblas-dev \
|
|
rocblas-dev && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/* && \
|
|
# I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able
|
|
# to locate the libraries. We run ldconfig ourselves to work around this packaging deficiency
|
|
ldconfig \
|
|
; fi
|
|
# Install uv as a system package
|
|
RUN curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=/usr/bin sh
|
|
ENV PATH="/root/.cargo/bin:${PATH}"
|
|
|
|
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
|
|
|
|
# Install grpcio-tools (the version in 22.04 is too old)
|
|
RUN pip install --user grpcio-tools==1.71.0 grpcio==1.71.0
|
|
|
|
COPY python/${BACKEND} /${BACKEND}
|
|
COPY backend.proto /${BACKEND}/backend.proto
|
|
COPY python/common/ /${BACKEND}/common
|
|
|
|
RUN cd /${BACKEND} && make
|
|
|
|
FROM scratch
|
|
ARG BACKEND=rerankers
|
|
COPY --from=builder /${BACKEND}/ / |