LocalAI/backend/Dockerfile.llama-cpp

ARG BASE_IMAGE=ubuntu:24.04
ARG GRPC_BASE_IMAGE=${BASE_IMAGE}


# The grpc target does one thing, it builds and installs GRPC.  This is in it's own layer so that it can be effectively cached by CI.
# You probably don't need to change anything here, and if you do, make sure that CI is adjusted so that the cache continues to work.
FROM ${GRPC_BASE_IMAGE} AS grpc

# This is a bit of a hack, but it's required in order to be able to effectively cache this layer in CI
ARG GRPC_MAKEFLAGS="-j4 -Otarget"
ARG GRPC_VERSION=v1.65.0
ARG CMAKE_FROM_SOURCE=false
# CUDA Toolkit 13.x compatibility: CMake 3.31.9+ fixes toolchain detection/arch table issues
ARG CMAKE_VERSION=3.31.10

ENV MAKEFLAGS=${GRPC_MAKEFLAGS}

WORKDIR /build

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        ca-certificates \
        build-essential curl libssl-dev \
        git wget && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

# Install CMake (the version in 22.04 is too old)
RUN <<EOT bash
    if [ "${CMAKE_FROM_SOURCE}" = "true" ]; then
        curl -L -s https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}.tar.gz -o cmake.tar.gz && tar xvf cmake.tar.gz && cd cmake-${CMAKE_VERSION} && ./configure && make && make install
    else
        apt-get update && \
        apt-get install -y \
            cmake && \
        apt-get clean && \
        rm -rf /var/lib/apt/lists/*
    fi
EOT

# We install GRPC to a different prefix here so that we can copy in only the build artifacts later
# saves several hundred MB on the final docker image size vs copying in the entire GRPC source tree
# and running make install in the target container
RUN git clone --recurse-submodules --jobs 4 -b ${GRPC_VERSION} --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
    mkdir -p /build/grpc/cmake/build && \
    cd /build/grpc/cmake/build && \
    sed -i "216i\  TESTONLY" "../../third_party/abseil-cpp/absl/container/CMakeLists.txt" && \
    cmake -DgRPC_INSTALL=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX:PATH=/opt/grpc ../.. && \
    make && \
    make install && \
    rm -rf /build

FROM ${BASE_IMAGE} AS builder
ARG CMAKE_FROM_SOURCE=false
ARG CMAKE_VERSION=3.31.10
# We can target specific CUDA ARCHITECTURES like --build-arg CUDA_DOCKER_ARCH='75;86;89;120'
ARG CUDA_DOCKER_ARCH
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
ARG CMAKE_ARGS
ENV CMAKE_ARGS=${CMAKE_ARGS}
ARG BACKEND=rerankers
ARG BUILD_TYPE
ENV BUILD_TYPE=${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=1.25.4
ARG UBUNTU_VERSION=2404

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        ccache git \
        ca-certificates \
        make \
        pkg-config libcurl4-openssl-dev \
        curl unzip \
        libssl-dev wget && \
    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 && \
        apt-get install -y libglm-dev cmake libxcb-dri3-0 libxcb-present0 libpciaccess0 \
            libpng-dev libxcb-keysyms1-dev libxcb-dri3-dev libx11-dev g++ gcc \
            libwayland-dev libxrandr-dev libxcb-randr0-dev libxcb-ewmh-dev \
            git python-is-python3 bison libx11-xcb-dev liblz4-dev libzstd-dev \
            ocaml-core ninja-build pkg-config libxml2-dev wayland-protocols python3-jsonschema \
            clang-format qtbase5-dev qt6-base-dev libxcb-glx0-dev sudo xz-utils && \
        wget "https://sdk.lunarg.com/sdk/download/1.4.328.1/linux/vulkansdk-linux-x86_64-1.4.328.1.tar.xz" && \
        tar -xf vulkansdk-linux-x86_64-1.4.328.1.tar.xz && \
        rm vulkansdk-linux-x86_64-1.4.328.1.tar.xz && \
        mkdir -p /opt/vulkan-sdk && \
        mv 1.4.328.1 /opt/vulkan-sdk/ && \
        cd /opt/vulkan-sdk/1.4.328.1 && \
        ./vulkansdk --no-deps --maxjobs \
            vulkan-loader \
            vulkan-validationlayers \
            vulkan-extensionlayer \
            vulkan-tools \
            shaderc && \
        cp -rfv /opt/vulkan-sdk/1.4.328.1/x86_64/bin/* /usr/bin/ && \
        cp -rfv /opt/vulkan-sdk/1.4.328.1/x86_64/lib/* /usr/lib/x86_64-linux-gnu/ && \
        cp -rfv /opt/vulkan-sdk/1.4.328.1/x86_64/include/* /usr/include/ && \
        cp -rfv /opt/vulkan-sdk/1.4.328.1/x86_64/share/* /usr/share/ && \
        rm -rf /opt/vulkan-sdk && \
        ldconfig && \
        apt-get clean && \
        rm -rf /var/lib/apt/lists/*
    fi
EOT

# CuBLAS requirements
RUN <<EOT bash
    if ( [ "${BUILD_TYPE}" = "cublas" ] || [ "${BUILD_TYPE}" = "l4t" ] ) && [ "${SKIP_DRIVERS}" = "false" ]; then
        apt-get update && \
        apt-get install -y  --no-install-recommends \
            software-properties-common pciutils
        if [ "amd64" = "$TARGETARCH" ]; then
            echo https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/x86_64/cuda-keyring_1.1-1_all.deb
            curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/x86_64/cuda-keyring_1.1-1_all.deb
        fi
        if [ "arm64" = "$TARGETARCH" ]; then
            curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/sbsa/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}
        if [ "arm64" = "$TARGETARCH" ]; then
            apt-get install -y --no-install-recommends \
            libcufile-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcudnn9-cuda-${CUDA_MAJOR_VERSION} cuda-cupti-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libnvjitlink-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
        fi
        apt-get clean && \
        rm -rf /var/lib/apt/lists/*
    fi
EOT


# https://github.com/NVIDIA/Isaac-GR00T/issues/343
RUN <<EOT bash
    if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "arm64" ]; then
        wget https://developer.download.nvidia.com/compute/cudss/0.6.0/local_installers/cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0_0.6.0-1_arm64.deb && \
        dpkg -i cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0_0.6.0-1_arm64.deb && \
        cp /var/cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0/cudss-*-keyring.gpg /usr/share/keyrings/ && \
        apt-get update && apt-get -y install cudss cudss-cuda-${CUDA_MAJOR_VERSION} && \
        wget https://developer.download.nvidia.com/compute/nvpl/25.5/local_installers/nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5_1.0-1_arm64.deb && \
        dpkg -i nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5_1.0-1_arm64.deb && \
        cp /var/nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5/nvpl-*-keyring.gpg /usr/share/keyrings/ && \
        apt-get update && apt-get install -y nvpl
    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

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

# Install CMake (the version in 22.04 is too old)
RUN <<EOT bash
    if [ "${CMAKE_FROM_SOURCE}" = "true" ]; then
        curl -L -s https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}.tar.gz -o cmake.tar.gz && tar xvf cmake.tar.gz && cd cmake-${CMAKE_VERSION} && ./configure && make && make install
    else
        apt-get update && \
        apt-get install -y \
            cmake && \
        apt-get clean && \
        rm -rf /var/lib/apt/lists/*
    fi
EOT

COPY --from=grpc /opt/grpc /usr/local


COPY . /LocalAI

RUN <<'EOT' bash
set -euxo pipefail

if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
  CUDA_ARCH_ESC="${CUDA_DOCKER_ARCH//;/\\;}"
  export CMAKE_ARGS="${CMAKE_ARGS:-} -DCMAKE_CUDA_ARCHITECTURES=${CUDA_ARCH_ESC}"
  echo "CMAKE_ARGS(env) = ${CMAKE_ARGS}"
  rm -rf /LocalAI/backend/cpp/llama-cpp-*-build
fi

if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
  cd /LocalAI/backend/cpp/llama-cpp
  make llama-cpp-fallback
  make llama-cpp-grpc
  make llama-cpp-rpc-server
else
  cd /LocalAI/backend/cpp/llama-cpp
  make llama-cpp-avx
  make llama-cpp-avx2
  make llama-cpp-avx512
  make llama-cpp-fallback
  make llama-cpp-grpc
  make llama-cpp-rpc-server
fi
EOT


# Copy libraries using a script to handle architecture differences
RUN make -BC /LocalAI/backend/cpp/llama-cpp package


FROM scratch


# Copy all available binaries (the build process only creates the appropriate ones for the target architecture)
COPY --from=builder /LocalAI/backend/cpp/llama-cpp/package/. ./