Files
LocalAI/backend/Dockerfile.go
T
Ettore Di Giacinto 294f7022f3 feat: do not bundle llama-cpp anymore (#5790)
* Build llama.cpp separately

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

* WIP

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

* WIP

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

* WIP

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

* Start to try to attach some tests

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

* Add git and small fixups

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

* fix: correctly autoload external backends

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

* Try to run AIO tests

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

* Slightly update the Makefile helps

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

* Adapt auto-bumper

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

* Try to run linux test

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

* Add llama-cpp into build pipelines

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

* Add default capability (for cpu)

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

* Drop llama-cpp specific logic from the backend loader

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

* drop grpc install in ci for tests

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

* fixups

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

* Pass by backends path for tests

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

* Build protogen at start

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

* fix(tests): set backends path consistently

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

* Correctly configure the backends path

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

* Try to build for darwin

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

* WIP

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

* Compile for metal on arm64/darwin

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

* Try to run build off from cross-arch

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

* Add to the backend index nvidia-l4t and cpu's llama-cpp backends

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

* Build also darwin-x86 for llama-cpp

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

* Disable arm64 builds temporary

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

* Test backend build on PR

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

* Fixup build backend reusable workflow

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

* pass by skip drivers

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

* Use crane

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

* Skip drivers

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

* Fixups

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

* x86 darwin

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

* Add packaging step for llama.cpp

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

* fixups

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

* Fix leftover from bark-cpp extraction

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

* Try to fix hipblas build

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-18 13:24:12 +02:00

132 lines
5.0 KiB
Go

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
ARG GO_VERSION=1.22.6
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential \
git ccache \
ca-certificates \
make cmake \
curl unzip \
libssl-dev && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# 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 Go
RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | tar -C /usr/local -xz
ENV PATH=$PATH:/root/go/bin:/usr/local/go/bin:/usr/local/bin
# Install grpc compilers
RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
RUN echo "TARGETARCH: $TARGETARCH"
# We need protoc installed, and the version in 22.04 is too old. We will create one as part installing the GRPC build below
# but that will also being in a newer version of absl which stablediffusion cannot compile with. This version of protoc is only
# here so that we can generate the grpc code for the stablediffusion build
RUN <<EOT bash
if [ "amd64" = "$TARGETARCH" ]; then
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v27.1/protoc-27.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
fi
if [ "arm64" = "$TARGETARCH" ]; then
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v27.1/protoc-27.1-linux-aarch_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
fi
EOT
COPY . /LocalAI
RUN cd /LocalAI && make protogen-go && make -C /LocalAI/backend/go/${BACKEND} build
FROM scratch
ARG BACKEND=rerankers
COPY --from=builder /LocalAI/backend/go/${BACKEND}/${BACKEND} ./
COPY --from=builder /LocalAI/backend/go/${BACKEND}/run.sh ./