wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+ android-arm64:
+ runs-on: ubuntu-latest
+
+ env:
+ NDK_VERSION: "29.0.14206865"
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: android-arm64
+ evict-old-files: 1d
+ save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+
+ - name: Set up JDK
+ uses: actions/setup-java@v5
+ with:
+ java-version: 17
+ distribution: temurin
+
+ - name: Setup Android SDK
+ uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
+ with:
+ log-accepted-android-sdk-licenses: false
+
+ - name: Install NDK
+ run: |
+ sdkmanager "ndk;${{ env.NDK_VERSION }}"
+ echo "ANDROID_NDK=${ANDROID_SDK_ROOT}/ndk/${{ env.NDK_VERSION }}" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK}/build/cmake/android.toolchain.cmake \
+ -DANDROID_ABI=arm64-v8a \
+ -DANDROID_PLATFORM=android-28 \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DGGML_BACKEND_DL=ON \
+ -DGGML_NATIVE=OFF \
+ -DGGML_CPU_ALL_VARIANTS=ON \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_BORINGSSL=ON \
+ -DGGML_RPC=ON
+ time cmake --build build --config Release -j $(nproc)
+
ubuntu-latest-rpc:
runs-on: ubuntu-latest
path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-${{ matrix.build }}.tar.gz
name: llama-bin-ubuntu-vulkan-${{ matrix.build }}.tar.gz
+ android-arm64:
+ runs-on: ubuntu-latest
+
+ env:
+ NDK_VERSION: "29.0.14206865"
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+ with:
+ fetch-depth: 0
+
+ - name: ccache
+ uses: ggml-org/ccache-action@v1.2.21
+ with:
+ key: android-arm64
+ evict-old-files: 1d
+
+ - name: Set up JDK
+ uses: actions/setup-java@v5
+ with:
+ java-version: 17
+ distribution: temurin
+
+ - name: Setup Android SDK
+ uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
+ with:
+ log-accepted-android-sdk-licenses: false
+
+ - name: Install NDK
+ run: |
+ sdkmanager "ndk;${{ env.NDK_VERSION }}"
+ echo "ANDROID_NDK=${ANDROID_SDK_ROOT}/ndk/${{ env.NDK_VERSION }}" >> $GITHUB_ENV
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build \
+ -DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK}/build/cmake/android.toolchain.cmake \
+ -DANDROID_ABI=arm64-v8a \
+ -DANDROID_PLATFORM=android-28 \
+ -DCMAKE_INSTALL_RPATH='$ORIGIN' \
+ -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
+ -DGGML_BACKEND_DL=ON \
+ -DGGML_NATIVE=OFF \
+ -DGGML_CPU_ALL_VARIANTS=ON \
+ -DLLAMA_FATAL_WARNINGS=ON \
+ -DGGML_OPENMP=OFF \
+ -DLLAMA_BUILD_BORINGSSL=ON \
+ ${{ env.CMAKE_ARGS }}
+ cmake --build build --config Release -j $(nproc)
+
+ - name: Determine tag name
+ id: tag
+ uses: ./.github/actions/get-tag-name
+
+ - name: Pack artifacts
+ id: pack_artifacts
+ run: |
+ cp LICENSE ./build/bin/
+ tar -czvf llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
+
+ - name: Upload artifacts
+ uses: actions/upload-artifact@v6
+ with:
+ path: llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz
+ name: llama-bin-android-arm64.tar.gz
+
ubuntu-24-openvino:
runs-on: ubuntu-24.04
- ubuntu-cpu
- ubuntu-vulkan
- ubuntu-24-openvino
+ - android-arm64
- macOS-cpu
- ios-xcode-build
- openEuler-cann
- [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-7.2-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ needs.ubuntu-24-openvino.outputs.openvino_version }}-x64.tar.gz)
+ **Android:**
+ - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz)
+
**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-arm64.zip)