LocalAI/backend/Dockerfile.python

ARG BASE_IMAGE=ubuntu:24.04
ARG APT_MIRROR=""
ARG APT_PORTS_MIRROR=""
# CI mirror of the CUDA aarch64 wheels from pypi.jetson-ai-lab.io, kept warm
# by .github/workflows/jetson-wheels.yml so l4t builds survive the upstream
# index's recurring multi-hour outages. The default (scratch) mounts an empty
# directory, which makes installRequirements fall through to the upstream
# index unchanged — local and Jetson-native builds are unaffected.
ARG JETSON_WHEELS_IMAGE=scratch

FROM ${JETSON_WHEELS_IMAGE} AS jetson-wheels
FROM alpine:3.22 AS ca-certificates

FROM ${BASE_IMAGE} AS builder
COPY --from=ca-certificates /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt

ENV SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt \
    CURL_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt \
    REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt \
    PIP_CERT=/etc/ssl/certs/ca-certificates.crt
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 UBUNTU_VERSION=2404
ARG APT_MIRROR
ARG APT_PORTS_MIRROR

RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 --mount=type=bind,source=.docker/install-build-proxy-ca.sh,target=/usr/local/sbin/install-build-proxy-ca --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mirror \
    APT_MIRROR="${APT_MIRROR}" APT_PORTS_MIRROR="${APT_PORTS_MIRROR}" sh /usr/local/sbin/apt-mirror && \
    apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        ccache \
        ca-certificates \
        espeak-ng \
        curl \
        libssl-dev \
        git wget \
        git-lfs \
        unzip clang \
        upx-ucl \
        curl python3-pip \
        python-is-python3 \
        python3-dev llvm \
        libnuma1 libgomp1 \
        python3-venv make cmake && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 <<EOT bash
    if [ "${UBUNTU_VERSION}" = "2404" ]; then
        pip install --break-system-packages --user --upgrade pip
    else
        pip install --upgrade pip
    fi
EOT


# Cuda
ENV PATH=/usr/local/cuda/bin:${PATH}

# HipBLAS requirements
ENV PATH=/opt/rocm/bin:${PATH}

# Vulkan requirements
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 <<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 && \
        apt-get install -y mesa-vulkan-drivers libdrm2
        # Mesa Vulkan ICD drivers (ANV/RADV/lavapipe) + their manifests. The
        # LunarG SDK below only provides the loader and shader tooling, not
        # hardware drivers — without Mesa, package-gpu-libs.sh has no ICD to
        # bundle and the packaged backend finds no GPU at runtime.
        if [ "amd64" = "$TARGETARCH" ]; then
            wget "https://sdk.lunarg.com/sdk/download/1.4.335.0/linux/vulkansdk-linux-x86_64-1.4.335.0.tar.xz" && \
            tar -xf vulkansdk-linux-x86_64-1.4.335.0.tar.xz && \
            rm vulkansdk-linux-x86_64-1.4.335.0.tar.xz && \
            mkdir -p /opt/vulkan-sdk && \
            mv 1.4.335.0 /opt/vulkan-sdk/ && \
            cd /opt/vulkan-sdk/1.4.335.0 && \
            ./vulkansdk --no-deps --maxjobs \
                vulkan-loader \
                vulkan-validationlayers \
                vulkan-extensionlayer \
                vulkan-tools \
                shaderc && \
            cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/bin/* /usr/bin/ && \
            cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/lib/* /usr/lib/x86_64-linux-gnu/ && \
            cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/include/* /usr/include/ && \
            cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/share/* /usr/share/ && \
            rm -rf /opt/vulkan-sdk
        fi
        if [ "arm64" = "$TARGETARCH" ]; then
            mkdir vulkan && cd vulkan && \
            curl -L -o vulkan-sdk.tar.xz https://github.com/mudler/vulkan-sdk-arm/releases/download/1.4.335.0/vulkansdk-ubuntu-24.04-arm-1.4.335.0.tar.xz && \
            tar -xvf vulkan-sdk.tar.xz && \
            rm vulkan-sdk.tar.xz && \
            cd 1.4.335.0 && \
            cp -rfv aarch64/bin/* /usr/bin/ && \
            cp -rfv aarch64/lib/* /usr/lib/aarch64-linux-gnu/ && \
            cp -rfv aarch64/include/* /usr/include/ && \
            cp -rfv aarch64/share/* /usr/share/ && \
            cd ../.. && \
            rm -rf vulkan
        fi
        ldconfig && \
        apt-get clean && \
        rm -rf /var/lib/apt/lists/*
    fi
EOT

# CuBLAS requirements
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 <<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
            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
            if [ "${CUDA_MAJOR_VERSION}" = "13" ]; then
                curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/sbsa/cuda-keyring_1.1-1_all.deb
            else
                curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/arm64/cuda-keyring_1.1-1_all.deb
            fi
        fi
        dpkg -i cuda-keyring_1.1-1_all.deb && \
        rm -f cuda-keyring_1.1-1_all.deb && \
        apt-get update && \
        apt-get install -y --no-install-recommends \
            cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
            cuda-nvrtc-dev-${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}-${CUDA_MINOR_VERSION}
        if [ "${CUDA_MAJOR_VERSION}" = "13" ] && [ "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 --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 <<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 --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 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 --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
        apt-get update && \
        apt-get install -y --no-install-recommends \
            hipblas-dev \
            hipblaslt-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 --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 if [ "${BUILD_TYPE}" = "hipblas" ]; then \
    ln -s /opt/rocm-**/lib/llvm/lib/libomp.so /usr/lib/libomp.so \
    ; fi

# Install uv as a system package
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=/usr/bin sh
ENV PATH="/root/.cargo/bin:${PATH}"
# Increase timeout for uv installs behind slow networks
ENV UV_HTTP_TIMEOUT=180
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 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 --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 <<EOT bash
    if [ "${UBUNTU_VERSION}" = "2404" ]; then
        pip install --break-system-packages --user grpcio-tools==1.71.0 grpcio==1.71.0
    else
        pip install grpcio-tools==1.71.0 grpcio==1.71.0
    fi
EOT


COPY backend/python/${BACKEND} /${BACKEND}
COPY backend/backend.proto /${BACKEND}/backend.proto
COPY backend/python/common/ /${BACKEND}/common
COPY scripts/build/package-gpu-libs.sh /package-gpu-libs.sh

# Optional per-backend source build toggle (e.g. vllm on CPU can set
# FROM_SOURCE=true to compile against the build host SIMD instead of
# pulling a prebuilt wheel). Default empty — most backends ignore it.
ARG FROM_SOURCE=""
ENV FROM_SOURCE=${FROM_SOURCE}

# Cache-buster for the per-backend `make` step. Most Python backends list
# unpinned deps (torch, transformers, vllm, ...), so a warm registry cache
# would otherwise freeze upstream versions indefinitely. CI passes a value
# that rolls weekly so the install layer is rebuilt at most once per week
# and picks up newer wheels from PyPI / nightly indexes.
ARG DEPS_REFRESH=initial

RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 --mount=type=bind,from=jetson-wheels,target=/jetson-wheels \
    cd /${BACKEND} && PORTABLE_PYTHON=true JETSON_WHEELS_DIR=/jetson-wheels make

# Package GPU libraries into the backend's lib directory.
#
# Must stay after the venv is built above: package-gpu-libs.sh inspects
# /${BACKEND}/venv to decide whether this backend already carries a complete
# cuDNN from pip, and bundles one only when it does not (issue #10905).
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 mkdir -p /${BACKEND}/lib && \
    TARGET_LIB_DIR="/${BACKEND}/lib" BUILD_TYPE="${BUILD_TYPE}" CUDA_MAJOR_VERSION="${CUDA_MAJOR_VERSION}" \
    bash /package-gpu-libs.sh "/${BACKEND}/lib"

# Run backend-specific packaging if a package.sh exists
RUN --mount=type=secret,id=build_proxy_ca,target=/run/secrets/build_proxy_ca,mode=0444 if [ -f "/${BACKEND}/package.sh" ]; then \
        cd /${BACKEND} && bash package.sh; \
    fi

FROM scratch
ARG BACKEND=rerankers
COPY --from=builder /${BACKEND}/ /