feat: package GPU libraries inside backend containers for unified base image

.github/workflows/image.yml

@@ -13,42 +13,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  hipblas-jobs:
-    uses: ./.github/workflows/image_build.yml
-    with:
-      tag-latest: ${{ matrix.tag-latest }}
-      tag-suffix: ${{ matrix.tag-suffix }}
-      build-type: ${{ matrix.build-type }}
-      cuda-major-version: ${{ matrix.cuda-major-version }}
-      cuda-minor-version: ${{ matrix.cuda-minor-version }}
-      platforms: ${{ matrix.platforms }}
-      runs-on: ${{ matrix.runs-on }}
-      base-image: ${{ matrix.base-image }}
-      grpc-base-image: ${{ matrix.grpc-base-image }}
-      aio: ${{ matrix.aio }}
-      makeflags: ${{ matrix.makeflags }}
-      ubuntu-version: ${{ matrix.ubuntu-version }}
-      ubuntu-codename: ${{ matrix.ubuntu-codename }}
-    secrets:
-      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
-      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
-      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
-      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
-    strategy:
-      matrix:
-        include:
-          - build-type: 'hipblas'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-hipblas'
-            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
-            grpc-base-image: "ubuntu:24.04"
-            runs-on: 'ubuntu-latest'
-            makeflags: "--jobs=3 --output-sync=target"
-            aio: "-aio-gpu-hipblas"
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'
-
+  # Unified base image build - GPU drivers are now packaged in individual backends
   core-image-build:
     uses: ./.github/workflows/image_build.yml
     with:
@@ -72,9 +37,10 @@ jobs:
       quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
       quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
     strategy:
-      #max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
+          # Unified base image for all platforms
+          # GPU-specific backends will be pulled at runtime and contain their own GPU libraries
           - build-type: ''
             platforms: 'linux/amd64,linux/arm64'
             tag-latest: 'auto'
@@ -86,101 +52,3 @@ jobs:
             skip-drivers: 'false'
             ubuntu-version: '2404'
             ubuntu-codename: 'noble'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "9"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            makeflags: "--jobs=4 --output-sync=target"
-            aio: "-aio-gpu-nvidia-cuda-12"
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            makeflags: "--jobs=4 --output-sync=target"
-            aio: "-aio-gpu-nvidia-cuda-13"
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-vulkan'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            makeflags: "--jobs=4 --output-sync=target"
-            aio: "-aio-gpu-vulkan"
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'
-          - build-type: 'intel'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
-            grpc-base-image: "ubuntu:24.04"
-            tag-suffix: '-gpu-intel'
-            runs-on: 'ubuntu-latest'
-            makeflags: "--jobs=3 --output-sync=target"
-            aio: "-aio-gpu-intel"
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'
-
-  gh-runner:
-    uses: ./.github/workflows/image_build.yml
-    with:
-      tag-latest: ${{ matrix.tag-latest }}
-      tag-suffix: ${{ matrix.tag-suffix }}
-      build-type: ${{ matrix.build-type }}
-      cuda-major-version: ${{ matrix.cuda-major-version }}
-      cuda-minor-version: ${{ matrix.cuda-minor-version }}
-      platforms: ${{ matrix.platforms }}
-      runs-on: ${{ matrix.runs-on }}
-      aio: ${{ matrix.aio }}
-      base-image: ${{ matrix.base-image }}
-      grpc-base-image: ${{ matrix.grpc-base-image }}
-      makeflags: ${{ matrix.makeflags }}
-      skip-drivers: ${{ matrix.skip-drivers }}
-      ubuntu-version: ${{ matrix.ubuntu-version }}
-      ubuntu-codename: ${{ matrix.ubuntu-codename }}
-    secrets:
-      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
-      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
-      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
-      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
-    strategy:
-      matrix:
-        include:
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "9"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-arm64'
-            base-image: "ubuntu:24.04"
-            runs-on: 'ubuntu-24.04-arm'
-            makeflags: "--jobs=4 --output-sync=target"
-            skip-drivers: 'true'
-            ubuntu-version: "2404"
-            ubuntu-codename: 'noble'
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-arm64-cuda-13'
-            base-image: "ubuntu:24.04"
-            runs-on: 'ubuntu-24.04-arm'
-            makeflags: "--jobs=4 --output-sync=target"
-            skip-drivers: 'false'
-            ubuntu-version: '2404'
-            ubuntu-codename: 'noble'

Dockerfile

@@ -14,7 +14,9 @@ RUN apt-get update && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# The requirements-drivers target is for BUILD_TYPE specific items.  If you need to install something specific to CUDA, or specific to ROCM, it goes here.
+# GPU drivers are no longer installed in the main image.
+# Each backend now packages its own GPU libraries (CUDA, ROCm, SYCL, Vulkan)
+# This allows for a unified base image that works with any backend.
 FROM requirements AS requirements-drivers
 
 ARG BUILD_TYPE
@@ -29,132 +31,6 @@ ARG UBUNTU_VERSION=2404
 RUN mkdir -p /run/localai
 RUN echo "default" > /run/localai/capability
 
-# 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 mesa-vulkan-drivers && \
-        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/* && \
-        echo "vulkan" > /run/localai/capability
-    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
-            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}-${CUDA_MINOR_VERSION} \
-            libcufft-dev-${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}-${CUDA_MINOR_VERSION}
-        fi
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/* && \
-        echo "nvidia-cuda-${CUDA_MAJOR_VERSION}" > /run/localai/capability
-    fi
-EOT
-
-RUN <<EOT bash
-    if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "arm64" ]; then
-        echo "nvidia-l4t-cuda-${CUDA_MAJOR_VERSION}" > /run/localai/capability
-    fi
-EOT
-
-# https://github.com/NVIDIA/Isaac-GR00T/issues/343
-RUN <<EOT bash
-    if [ "${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/* && \
-        echo "amd" > /run/localai/capability && \
-        # 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 if [ "${BUILD_TYPE}" = "hipblas" ]; then \
-    ln -s /opt/rocm-**/lib/llvm/lib/libomp.so /usr/lib/libomp.so \
-    ; fi
-
-RUN expr "${BUILD_TYPE}" = intel && echo "intel" > /run/localai/capability || echo "not intel"
-
-# Cuda
-ENV PATH=/usr/local/cuda/bin:${PATH}
-
-# HipBLAS requirements
-ENV PATH=/opt/rocm/bin:${PATH}
-
 ###################################
 ###################################
 

backend/Dockerfile.python

@@ -174,9 +174,15 @@ 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
 
 RUN cd /${BACKEND} && PORTABLE_PYTHON=true make
 
+# Package GPU libraries into the backend's lib directory
+RUN mkdir -p /${BACKEND}/lib && \
+    TARGET_LIB_DIR="/${BACKEND}/lib" BUILD_TYPE="${BUILD_TYPE}" CUDA_MAJOR_VERSION="${CUDA_MAJOR_VERSION}" \
+    bash /package-gpu-libs.sh "/${BACKEND}/lib"
+
 FROM scratch
 ARG BACKEND=rerankers
 COPY --from=builder /${BACKEND}/ /

backend/cpp/llama-cpp/package.sh

@@ -6,6 +6,7 @@
 set -e
 
 CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
 
 # Create lib directory
 mkdir -p $CURDIR/package/lib
@@ -37,6 +38,15 @@ else
     exit 1
 fi
 
+# Package GPU libraries based on BUILD_TYPE
+# The GPU library packaging script will detect BUILD_TYPE and copy appropriate GPU libraries
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
 echo "Packaging completed successfully" 
 ls -liah $CURDIR/package/
 ls -liah $CURDIR/package/lib/

backend/go/stablediffusion-ggml/package.sh

@@ -6,6 +6,7 @@
 set -e
 
 CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
 
 # Create lib directory
 mkdir -p $CURDIR/package/lib
@@ -50,6 +51,15 @@ else
     exit 1
 fi
 
+# Package GPU libraries based on BUILD_TYPE
+# The GPU library packaging script will detect BUILD_TYPE and copy appropriate GPU libraries
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
 echo "Packaging completed successfully"
 ls -liah $CURDIR/package/
 ls -liah $CURDIR/package/lib/

backend/go/whisper/package.sh

@@ -6,6 +6,7 @@
 set -e
 
 CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
 
 # Create lib directory
 mkdir -p $CURDIR/package/lib
@@ -50,6 +51,15 @@ else
     exit 1
 fi
 
+# Package GPU libraries based on BUILD_TYPE
+# The GPU library packaging script will detect BUILD_TYPE and copy appropriate GPU libraries
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
 echo "Packaging completed successfully"
 ls -liah $CURDIR/package/
 ls -liah $CURDIR/package/lib/