openvino: OV 2026.2, context-shift, Q5_1 support, gemma4 dense/embedding, and -fa off

.devops/openvino.Dockerfile

@@ -1,17 +1,17 @@
-ARG OPENVINO_VERSION_MAJOR=2026.0
-ARG OPENVINO_VERSION_FULL=2026.0.0.20965.c6d6a13a886
+ARG OPENVINO_VERSION_MAJOR=2026.2
+ARG OPENVINO_VERSION_FULL=2026.2.0.21903.52ddc073857
 ARG UBUNTU_VERSION=24.04
 
 # Intel GPU driver versions. https://github.com/intel/compute-runtime/releases
-ARG IGC_VERSION=v2.30.1
-ARG IGC_VERSION_FULL=2_2.30.1+20950
-ARG COMPUTE_RUNTIME_VERSION=26.09.37435.1
-ARG COMPUTE_RUNTIME_VERSION_FULL=26.09.37435.1-0
-ARG IGDGMM_VERSION=22.9.0
+ARG IGC_VERSION=v2.34.4
+ARG IGC_VERSION_FULL=2_2.34.4+21428
+ARG COMPUTE_RUNTIME_VERSION=26.18.38308.1
+ARG COMPUTE_RUNTIME_VERSION_FULL=26.18.38308.1-0
+ARG IGDGMM_VERSION=22.10.0
 
 # Intel NPU driver versions. https://github.com/intel/linux-npu-driver/releases
-ARG NPU_DRIVER_VERSION=v1.32.0
-ARG NPU_DRIVER_FULL=v1.32.0.20260402-23905121947
+ARG NPU_DRIVER_VERSION=v1.33.0
+ARG NPU_DRIVER_FULL=v1.33.0.20260529-26625960453
 ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2
 
 # Optional proxy build arguments
@@ -46,13 +46,18 @@ RUN apt-get update && \
         intel-opencl-icd && \
     rm -rf /var/lib/apt/lists/*
 
-# Install OpenVINO for Ubuntu 24.04
+# OpenVINO toolkit and GPU/NPU drivers are cached via BuildKit cache mounts to avoid re-downloading on rebuilds.
+# 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_${OPENVINO_VERSION_MAJOR} && \
+RUN --mount=type=cache,target=/var/cache/openvino,sharing=locked \
+    mkdir -p /opt/intel && \
+    TGZ=/var/cache/openvino/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz && \
+    if [ ! -f "$TGZ" ]; then \
+        wget -O "$TGZ" https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION_MAJOR}/linux/openvino_toolkit_ubuntu24_${OPENVINO_VERSION_FULL}_x86_64.tgz; \
+    fi && \
+    tar -xf "$TGZ" -C /opt/intel/ && \
+    mv /opt/intel/openvino_toolkit_ubuntu24_${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 - && \
@@ -68,14 +73,14 @@ COPY . .
 RUN bash -c "source ${OpenVINO_DIR}/setupvars.sh && \
     cmake -B build/ReleaseOV -G Ninja \
         -DCMAKE_BUILD_TYPE=Release \
+        -DLLAMA_BUILD_TESTS=OFF \
         -DGGML_OPENVINO=ON && \
-    cmake --build build/ReleaseOV -j$(nproc)"
+    cmake --build build/ReleaseOV --parallel "
 
-# Copy all necessary libraries
+# Copy all necessary libraries (build outputs + OpenVINO runtime libs)
 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 ${OpenVINO_DIR}/lib/intel64 -name '*.so*' -exec cp -P {} /app/lib \;
+    find build/ReleaseOV -name '*.so*' -exec cp -P {} /app/lib \; && \
+    find "${OpenVINO_DIR}/runtime/lib/intel64" -name '*.so*' -exec cp -P {} /app/lib \;
 
 # Create runtime directories and copy binaries
 RUN mkdir -p /app/full \
@@ -120,33 +125,41 @@ ARG IGC_VERSION_FULL
 ARG COMPUTE_RUNTIME_VERSION
 ARG COMPUTE_RUNTIME_VERSION_FULL
 ARG IGDGMM_VERSION
-RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
-    && wget https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
-    && wget https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-ocloc-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-opencl-icd-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libze-intel-gpu1-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
-    && wget https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
-    && dpkg --install *.deb \
-    && rm -rf /tmp/neo/
+RUN --mount=type=cache,target=/var/cache/intel-gpu,sharing=locked \
+    set -eux; \
+    cd /var/cache/intel-gpu; \
+    for url in \
+        https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
+        https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
+        https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
+        https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
+        https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
+        https://github.com/intel/compute-runtime/releases/download/${COMPUTE_RUNTIME_VERSION}/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb ; do \
+        f=$(basename "$url"); \
+        [ -f "$f" ] || wget -q -O "$f" "$url"; \
+    done; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends ./*.deb; \
+    rm -rf /var/lib/apt/lists/*
 
 # Install NPU drivers
 ARG NPU_DRIVER_VERSION
 ARG NPU_DRIVER_FULL
 ARG LIBZE1_VERSION
-RUN mkdir /tmp/npu/ && cd /tmp/npu/ \
-    && wget https://github.com/intel/linux-npu-driver/releases/download/${NPU_DRIVER_VERSION}/linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz \
-    && tar -xf linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz \
-    && dpkg --install *.deb \
-    && rm -rf /tmp/npu/
-
-RUN cd /tmp \
-    && wget https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260324T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb \
-    && dpkg --install libze1_${LIBZE1_VERSION}_amd64.deb \
-    && rm libze1_${LIBZE1_VERSION}_amd64.deb
+RUN --mount=type=cache,target=/var/cache/intel-npu,sharing=locked \
+    set -eux; \
+    TGZ=/var/cache/intel-npu/linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz; \
+    if [ ! -f "$TGZ" ]; then \
+        wget -q -O "$TGZ" https://github.com/intel/linux-npu-driver/releases/download/${NPU_DRIVER_VERSION}/linux-npu-driver-${NPU_DRIVER_FULL}-ubuntu2404.tar.gz; \
+    fi; \
+    DEB=/var/cache/intel-npu/libze1_${LIBZE1_VERSION}_amd64.deb; \
+    if [ ! -f "$DEB" ]; then \
+        wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260324T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
+    fi; \
+    mkdir /tmp/npu/ && cd /tmp/npu/ && tar -xf "$TGZ" && cp "$DEB" .; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends ./*.deb; \
+    rm -rf /tmp/npu/ /var/lib/apt/lists/*
 
 COPY --from=build /app/lib/ /app/
 
@@ -166,22 +179,26 @@ RUN apt-get update && \
     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 && \
+    python3 -m venv /openvino-venv && \
+    /openvino-venv/bin/pip install --no-cache-dir --upgrade pip setuptools wheel && \
+    /openvino-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 \"$@\"", "--"]
+# Activate the venv
+ENV VIRTUAL_ENV=/openvino-venv \
+    PATH=/openvino-venv/bin:$PATH
+
+ENTRYPOINT ["/app/tools.sh"]
 
 
 ### Light, CLI only
 FROM base AS light
 
-COPY --from=build /app/full/llama-cli /app/
+COPY --from=build /app/full/llama-cli /app/full/llama-completion /app/
 
 WORKDIR /app
 

.github/actions/windows-setup-openvino/action.yml

@@ -0,0 +1,24 @@
+name: "Windows - Setup OpenVINO Toolkit"
+description: "Setup OpenVINO Toolkit for Windows"
+inputs:
+  path:
+    description: "Installation path"
+    required: true
+  version_major:
+    description: "OpenVINO major version (e.g., 2026.2)"
+    required: true
+  version_full:
+    description: "OpenVINO full version"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Download and extract OpenVINO Runtime
+      shell: powershell
+      run: |
+        $url = "https://storage.openvinotoolkit.org/repositories/openvino/packages/${{ inputs.version_major }}/windows/openvino_toolkit_windows_${{ inputs.version_full }}_x86_64.zip"
+        $out = "openvino.zip"
+        Invoke-WebRequest -Uri $url -OutFile $out
+        Expand-Archive -Path $out -DestinationPath ${{ inputs.path }} -Force
+        Remove-Item $out

.github/workflows/build-cache.yml

@@ -68,8 +68,8 @@ jobs:
 
     env:
       # Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
-      OPENVINO_VERSION_MAJOR: "2026.0"
-      OPENVINO_VERSION_FULL: "2026.0.0.20965.c6d6a13a886"
+      OPENVINO_VERSION_MAJOR: "2026.2"
+      OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
 
     steps:
       - name: Clone
@@ -91,6 +91,34 @@ jobs:
           version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
           version_full: ${{ env.OPENVINO_VERSION_FULL }}
 
+  windows-2022-openvino-cache:
+    runs-on: windows-2022
+
+    env:
+      # Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
+      OPENVINO_VERSION_MAJOR: "2026.2"
+      OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Setup Cache
+        uses: actions/cache@v5
+        id: cache-openvino
+        with:
+          path: ./openvino_toolkit
+          key: cache-gha-openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
+
+      - name: Setup OpenVINO Toolkit
+        if: steps.cache-openvino.outputs.cache-hit != 'true'
+        uses: ./.github/actions/windows-setup-openvino
+        with:
+          path: ./openvino_toolkit
+          version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
+          version_full: ${{ env.OPENVINO_VERSION_FULL }}
+
   windows-2022-rocm-cache:
     runs-on: windows-2022
 

.github/workflows/build-openvino.yml

@@ -37,14 +37,10 @@ jobs:
   ubuntu-24-openvino:
     runs-on: [self-hosted, Linux, Intel, OpenVINO]
 
-    concurrency:
-      group: openvino-gpu-${{ github.head_ref || github.ref }}
-      cancel-in-progress: false
-
     env:
       # Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
-      OPENVINO_VERSION_MAJOR: "2026.0"
-      OPENVINO_VERSION_FULL: "2026.0.0.20965.c6d6a13a886"
+      OPENVINO_VERSION_MAJOR: "2026.2"
+      OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
 
     steps:
       - name: Clone
@@ -78,7 +74,7 @@ jobs:
           cmake -B build/ReleaseOV -G Ninja \
             -DCMAKE_BUILD_TYPE=Release \
             -DGGML_OPENVINO=ON
-          time cmake --build build/ReleaseOV --config Release -j $(nproc)
+          time cmake --build build/ReleaseOV --config Release --parallel
 
       - name: Test (CPU)
         id: cmake_test_cpu
@@ -93,4 +89,81 @@ jobs:
         run: |
           cd ${{ github.workspace }}
           export GGML_OPENVINO_DEVICE=GPU
-          ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
+          ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 3000
+
+  openvino-windows-2022:
+    runs-on: windows-2022
+
+    env:
+      # Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
+      OPENVINO_VERSION_MAJOR: "2026.2"
+      OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: ccache
+        uses: ggml-org/ccache-action@v1.2.21
+        with:
+          key: openvino-windows-2022
+          variant: ccache
+          evict-old-files: 1d
+          save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+      - name: Setup Cache
+        uses: actions/cache@v5
+        id: cache-openvino
+        with:
+          path: ./openvino_toolkit
+          key: cache-gha-openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
+
+      - name: Setup OpenVINO Toolkit
+        if: steps.cache-openvino.outputs.cache-hit != 'true'
+        uses: ./.github/actions/windows-setup-openvino
+        with:
+          path: ./openvino_toolkit
+          version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
+          version_full: ${{ env.OPENVINO_VERSION_FULL }}
+
+      - name: Install OpenCL using vcpkg
+        shell: powershell
+        run: |
+          git clone https://github.com/microsoft/vcpkg C:\vcpkg
+          C:\vcpkg\bootstrap-vcpkg.bat
+          C:\vcpkg\vcpkg install opencl
+
+      - name: Build
+        id: cmake_build
+        shell: cmd
+        run: |
+          REM Find extracted OpenVINO folder dynamically
+          for /d %%i in (openvino_toolkit\*) do set OPENVINO_ROOT=%%i
+
+          if not exist "%OPENVINO_ROOT%\runtime\cmake\OpenVINOConfig.cmake" (
+              echo ERROR: OpenVINOConfig.cmake not found
+              exit /b 1
+          )
+
+          call "%OPENVINO_ROOT%\setupvars.bat"
+
+          cmake -B build\ReleaseOV -G "Visual Studio 17 2022" ^
+            -A x64 ^
+            -DCMAKE_BUILD_TYPE=Release ^
+            -DGGML_OPENVINO=ON ^
+            -DCMAKE_TOOLCHAIN_FILE=C:\vcpkg\scripts\buildsystems\vcpkg.cmake
+
+          cmake --build build\ReleaseOV --config Release -- /m
+
+      - name: Test (CPU)
+        id: cmake_test_cpu
+        shell: cmd
+        # TODO: fix and re-enable the `test-llama-archs` test below
+        run: |
+          REM Find extracted OpenVINO folder dynamically
+          for /d %%i in (openvino_toolkit\*) do set OPENVINO_ROOT=%%i
+          call "%OPENVINO_ROOT%\setupvars.bat"
+
+          cd build
+          ctest --test-dir ReleaseOV -L main -E "test-llama-archs" -C Release --verbose --timeout 3000

.github/workflows/build-self-hosted.yml

@@ -264,14 +264,10 @@ jobs:
   gpu-openvino-low-perf:
     runs-on: [self-hosted, Linux, Intel, OpenVINO]
 
-    concurrency:
-      group: openvino-gpu-${{ github.head_ref || github.ref }}
-      cancel-in-progress: false
-
     env:
       # Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
-      OPENVINO_VERSION_MAJOR: "2026.0"
-      OPENVINO_VERSION_FULL: "2026.0.0.20965.c6d6a13a886"
+      OPENVINO_VERSION_MAJOR: "2026.2"
+      OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
 
     steps:
       - name: Clone