SDPA f32

.devops/openvino.Dockerfile

@@ -0,0 +1,134 @@
+ARG OPENVINO_VERSION_MAJOR=2025.2
+ARG OPENVINO_VERSION_FULL=2025.2.0.19140.c01cd93e24d
+ARG UBUNTU_VERSION=24.04
+
+# Optional proxy build arguments - empty by default
+ARG http_proxy=
+ARG https_proxy=
+
+## Build Image
+FROM ubuntu:${UBUNTU_VERSION} AS build
+
+# Pass proxy args to build stage
+ARG http_proxy
+ARG https_proxy
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        ca-certificates \
+        gnupg \
+        wget \
+        git \
+        cmake \
+        ninja-build \
+        build-essential \
+        libtbb12 \
+        libcurl4-openssl-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install OpenVINO for Ubuntu 24.04
+ARG OPENVINO_VERSION_MAJOR
+ARG OPENVINO_VERSION_FULL
+RUN mkdir -p /opt/intel && \
+    wget https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION_MAJOR}/linux/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz && \
+    tar -xf openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz && \
+    mv openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64 /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} && \
+    cd /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} && \
+    echo "Y" | ./install_dependencies/install_openvino_dependencies.sh && \
+    cd - && \
+    ln -s /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} /opt/intel/openvino
+
+ENV OpenVINO_DIR=/opt/intel/openvino
+
+WORKDIR /app
+
+COPY . .
+
+# Build Stage
+RUN bash -c "source ${OpenVINO_DIR}/setupvars.sh && \
+    cmake -B build/ReleaseOV -G Ninja \
+        -DCMAKE_BUILD_TYPE=Release \
+        -DGGML_OPENVINO=ON && \
+    cmake --build build/ReleaseOV -j$(nproc)"
+
+# Copy all necessary libraries
+RUN mkdir -p /app/lib && \
+    find build/ReleaseOV -name '*.so*' -exec cp {} /app/lib \; && \
+    find ${OpenVINO_DIR}/runtime/lib/intel64 -name '*.so*' -exec cp -P {} /app/lib \; 2>/dev/null || \
+    find ${OpenVINO_DIR}/lib/intel64 -name '*.so*' -exec cp -P {} /app/lib \;
+
+# Create runtime directories and copy binaries
+RUN mkdir -p /app/full \
+    && cp build/ReleaseOV/bin/* /app/full/ \
+    && cp *.py /app/full \
+    && cp -r gguf-py /app/full \
+    && cp -r requirements /app/full \
+    && cp requirements.txt /app/full \
+    && cp .devops/tools.sh /app/full/tools.sh
+
+## Base Runtime Image
+FROM ubuntu:${UBUNTU_VERSION} AS base
+
+# Pass proxy args to runtime stage
+ARG http_proxy
+ARG https_proxy
+
+RUN apt-get update \
+    && apt-get install -y libgomp1 libtbb12 curl\
+    && apt autoremove -y \
+    && apt clean -y \
+    && rm -rf /tmp/* /var/tmp/* \
+    && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
+    && find /var/cache -type f -delete
+
+COPY --from=build /app/lib/ /app/
+
+### Full (all binaries)
+FROM base AS full
+
+ARG http_proxy
+ARG https_proxy
+
+COPY --from=build /app/full /app/
+
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    git \
+    python3 \
+    python3-venv \
+    python3-pip && \
+    python3 -m venv /ov-venv && \
+    /ov-venv/bin/pip install --no-cache-dir --upgrade pip setuptools wheel && \
+    /ov-venv/bin/pip install --no-cache-dir -r requirements.txt && \
+    apt-get autoremove -y && \
+    apt-get clean && \
+    rm -rf /tmp/* /var/tmp/* && \
+    find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
+    find /var/cache -type f -delete
+
+ENTRYPOINT ["/bin/bash", "-c", "source /ov-venv/bin/activate && exec /app/tools.sh \"$@\"", "--"]
+
+
+### Light, CLI only
+FROM base AS light
+
+COPY --from=build /app/full/llama-cli /app/
+
+WORKDIR /app
+
+ENTRYPOINT [ "/app/llama-cli" ]
+
+### Server, Server only
+FROM base AS server
+
+ENV LLAMA_ARG_HOST=0.0.0.0
+
+COPY --from=build /app/full/llama-server /app/
+
+WORKDIR /app
+
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
+ENTRYPOINT [ "/app/llama-server" ]

.github/workflows/build.yml

@@ -638,6 +638,45 @@ jobs:
             -DGGML_SYCL_F16=ON
           cmake --build build --config Release -j $(nproc)
 
+  ubuntu-24-cmake-openvino:
+      runs-on: ubuntu-24.04
+
+      steps:
+        - name: Clone
+          id: checkout
+          uses: actions/checkout@v4
+
+        - name: ccache
+          uses: hendrikmuhs/[email protected]
+          with:
+            key: ubuntu-24-cmake-openvino-no-preset-v1
+            evict-old-files: 1d
+
+        - name: Dependencies
+          id: depends
+          run: |
+            export OPENVINO_VERSION_MAJOR=2025.2
+            export OPENVINO_VERSION_FULL=2025.2.0.19140.c01cd93e24d
+            sudo apt-get update
+            sudo apt-get install -y build-essential libcurl4-openssl-dev libtbb12 cmake ninja-build python3-pip curl wget tar
+            sudo mkdir -p /opt/intel
+            wget -O openvino_${OPENVINO_VERSION_MAJOR}.tgz https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION_MAJOR}/linux/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz
+            tar -xf openvino_${OPENVINO_VERSION_MAJOR}.tgz
+            sudo mv openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64 /opt/intel/openvino_${OPENVINO_VERSION_MAJOR}
+            rm openvino_${OPENVINO_VERSION_MAJOR}.tgz
+            cd /opt/intel/openvino_${OPENVINO_VERSION_MAJOR}
+            echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh && cd -
+            sudo ln -s /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} /opt/intel/openvino
+
+        - name: Build
+          id: cmake_build
+          run: |
+            source /opt/intel/openvino/setupvars.sh
+            cmake -B build/ReleaseOV -G Ninja \
+              -DCMAKE_BUILD_TYPE=Release \
+              -DGGML_OPENVINO=ON
+            cmake --build build/ReleaseOV --config Release -j $(nproc)
+
   build-linux-cross:
     uses: ./.github/workflows/build-linux-cross.yml
 

.github/workflows/docker.yml

@@ -44,6 +44,7 @@ jobs:
           - { tag: "musa", dockerfile: ".devops/musa.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true }
           - { tag: "intel", dockerfile: ".devops/intel.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true }
           - { tag: "vulkan", dockerfile: ".devops/vulkan.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false }
+          - { tag: "openvino", dockerfile: ".devops/openvino.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false }
           # Note: the rocm images are failing due to a compiler error and are disabled until this is fixed to allow the workflow to complete
           #- {tag: "rocm", dockerfile: ".devops/rocm.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, free_disk_space: true }
     steps:

.github/workflows/release.yml

@@ -240,6 +240,63 @@ jobs:
           path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip
           name: llama-bin-ubuntu-vulkan-x64.zip
 
+  ubuntu-24-openvino:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: ccache
+        uses: hendrikmuhs/[email protected]
+        with:
+          key: ubuntu-24-cmake-openvino-release-no-preset-v1 
+          evict-old-files: 1d
+
+      - name: Dependencies
+        id: depends
+        run: |
+          export OPENVINO_VERSION_MAJOR=2025.2
+          export OPENVINO_VERSION_FULL=2025.2.0.19140.c01cd93e24d
+          sudo apt-get update
+          sudo apt-get install -y build-essential libcurl4-openssl-dev libtbb12 cmake ninja-build python3-pip curl wget tar
+          sudo mkdir -p /opt/intel
+          wget -O openvino_${OPENVINO_VERSION_MAJOR}.tgz https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION_MAJOR}/linux/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz
+          tar -xf openvino_${OPENVINO_VERSION_MAJOR}.tgz
+          sudo mv openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64 /opt/intel/openvino_${OPENVINO_VERSION_MAJOR}
+          rm openvino_${OPENVINO_VERSION_MAJOR}.tgz
+          cd /opt/intel/openvino_${OPENVINO_VERSION_MAJOR}
+          echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh && cd -
+          sudo ln -s /opt/intel/openvino_${OPENVINO_VERSION_MAJOR} /opt/intel/openvino
+
+      - name: Build
+        id: cmake_build
+        run: |
+          source /opt/intel/openvino/setupvars.sh
+          cmake -B build/ReleaseOV -G Ninja \
+            -DCMAKE_BUILD_TYPE=Release \
+            -DGGML_OPENVINO=ON
+          cmake --build build/ReleaseOV --config Release -j $(nproc)
+
+      - name: Determine tag name
+        id: tag
+        uses: ./.github/actions/get-tag-name
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        run: |
+          cp LICENSE ./build/ReleaseOV/bin/
+          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-x64.zip ./build/ReleaseOV/bin/*
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-x64.zip
+          name: llama-bin-ubuntu-openvino-x64.zip
+
   windows-cpu:
     runs-on: windows-2025
 

CMakePresets.json

@@ -1,6 +1,26 @@
 {
   "version": 4,
   "configurePresets": [
+    {
+        "name": "ReleaseOV",
+        "generator": "Ninja",
+        "binaryDir": "${sourceDir}/build/${presetName}",
+        "installDir": "${sourceDir}/build/install/${presetName}",
+        "cacheVariables": {
+            "CMAKE_BUILD_TYPE": "Release",
+            "GGML_OPENVINO": true,
+            "OpenVINO_DIR": "$env{OPENVINO_LLAMA_PATH}/build/Release"
+        }
+    },
+    {
+        "name": "ReleaseCPU",
+        "generator": "Ninja",
+        "binaryDir": "${sourceDir}/build/${presetName}",
+        "installDir": "${sourceDir}/build/install/${presetName}",
+        "cacheVariables": {
+            "CMAKE_BUILD_TYPE": "Release"
+        }
+    },
     {
         "name":  "base",
         "hidden": true,

ci/run.sh

@@ -22,6 +22,9 @@
 # # with MUSA support
 # GG_BUILD_MUSA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
 #
+# # with OPENVINO support
+# GG_BUILD_OPENVINO=1 GG_BUILD_LOW_PERF=1 GGML_OPENVINO_DEVICE=CPU bash ./ci/run.sh ./tmp/results ./tmp/mnt
+#
 
 if [ -z "$2" ]; then
     echo "usage: $0 <output-dir> <mnt-dir>"
@@ -93,6 +96,15 @@ if [ ! -z ${GG_BUILD_MUSA} ]; then
     MUSA_ARCH=${MUSA_ARCH:-21}
     CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_MUSA=ON -DMUSA_ARCHITECTURES=${MUSA_ARCH}"
 fi
+
+if [ ! -z ${GG_BUILD_OPENVINO} ]; then
+    if [ -z ${OpenVINO_DIR} ]; then
+        echo "OpenVINO_DIR not found, please install OpenVINO via archives and enable it by:"
+        echo "source /opt/intel/openvino/setupvars.sh"
+        exit 1
+    fi
+    CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_OPENVINO=ON"
+fi
 ## helpers
 
 # download a file if it does not exist or if it is outdated