From 302e2c2652ba42992f6df581a191a076151fce94 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 25 May 2026 20:54:54 +0300 Subject: [PATCH] ci : reduce PR jobs by matching backend paths (#23675) * ci : disable SYCL f16 builds * ci : extract android and hip into separate workflows * ci : move webgpu to separate workflow * ci : move the rpc to a separate workflow * ci : extract s309x and ppcl jobs * ci : extract opencl job into a separate workflow --- .github/workflows/build-android.yml | 50 +++ .github/workflows/build-hip.yml | 167 ++++++++++ .github/workflows/build-ibm.yml | 150 +++++++++ .github/workflows/build-opencl.yml | 83 +++++ .github/workflows/build-riscv.yml | 70 ++++ .github/workflows/build-rpc.yml | 67 ++++ .github/workflows/build-sycl.yml | 4 +- .github/workflows/build-webgpu.yml | 186 +++++++++++ .github/workflows/build.yml | 477 ---------------------------- .github/workflows/release.yml | 5 +- 10 files changed, 775 insertions(+), 484 deletions(-) create mode 100644 .github/workflows/build-hip.yml create mode 100644 .github/workflows/build-ibm.yml create mode 100644 .github/workflows/build-opencl.yml create mode 100644 .github/workflows/build-rpc.yml create mode 100644 .github/workflows/build-webgpu.yml diff --git a/.github/workflows/build-android.yml b/.github/workflows/build-android.yml index f4c3fd669..99c3659b9 100644 --- a/.github/workflows/build-android.yml +++ b/.github/workflows/build-android.yml @@ -91,3 +91,53 @@ jobs: with: name: llama-cpp-android-arm64-cpu path: pkg-adb/llama.cpp + + 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) diff --git a/.github/workflows/build-hip.yml b/.github/workflows/build-hip.yml new file mode 100644 index 000000000..0c20fa3af --- /dev/null +++ b/.github/workflows/build-hip.yml @@ -0,0 +1,167 @@ +name: CI (hip) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build-hip.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-hip.yml', + 'ggml/src/ggml-cuda/**' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + +jobs: + + ubuntu-22-hip: + runs-on: ubuntu-22.04 + container: rocm/dev-ubuntu-22.04:6.1.2 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ubuntu-22-hip + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Build with native CMake HIP support + id: cmake_build + run: | + cmake -B build -S . \ + -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ + -DGGML_HIP_ROCWMMA_FATTN=ON \ + -DGPU_TARGETS="gfx1030" \ + -DGGML_HIP=ON + cmake --build build --config Release -j $(nproc) + + windows-latest-hip: + runs-on: windows-2022 + + env: + # Make sure this is in sync with build-cache.yml + HIPSDK_INSTALLER_VERSION: "26.Q1" + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Grab rocWMMA package + id: grab_rocwmma + run: | + curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb" + 7z x rocwmma.deb + 7z x data.tar + + - name: Use ROCm Installation Cache + uses: actions/cache@v5 + id: cache-rocm + with: + path: C:\Program Files\AMD\ROCm + key: rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }} + + - name: Setup ROCm + if: steps.cache-rocm.outputs.cache-hit != 'true' + uses: ./.github/actions/windows-setup-rocm + with: + version: ${{ env.HIPSDK_INSTALLER_VERSION }} + + - name: Verify ROCm + id: verify + run: | + # Find and test ROCm installation + $clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1 + if (-not $clangPath) { + Write-Error "ROCm installation not found" + exit 1 + } + & $clangPath.FullName --version + + - name: Install ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ${{ github.job }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Build + id: cmake_build + run: | + $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) + $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" + cmake -G "Unix Makefiles" -B build -S . ` + -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` + -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` + -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" ` + -DCMAKE_BUILD_TYPE=Release ` + -DLLAMA_BUILD_BORINGSSL=ON ` + -DROCM_DIR="${env:HIP_PATH}" ` + -DGGML_HIP=ON ` + -DGGML_HIP_ROCWMMA_FATTN=ON ` + -DGPU_TARGETS="gfx1100" ` + -DGGML_RPC=ON + cmake --build build -j ${env:NUMBER_OF_PROCESSORS} + + ubuntu-22-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libssl-dev + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ubuntu-22-musa + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . \ + -DGGML_MUSA=ON + time cmake --build build --config Release -j $(nproc) diff --git a/.github/workflows/build-ibm.yml b/.github/workflows/build-ibm.yml new file mode 100644 index 000000000..1742894b9 --- /dev/null +++ b/.github/workflows/build-ibm.yml @@ -0,0 +1,150 @@ +name: CI (ibm) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build-ibm.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-ibm.yml', + 'ggml/src/ggml-cpu/**' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + +jobs: + + ubuntu-24-s390x: + runs-on: ubuntu-24.04-s390x + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Build Dependencies + id: build_depends + run: | + sudo apt-get update + sudo apt-get install -y --no-install-recommends \ + python3 python3-pip python3-dev python3-wheel \ + libjpeg-dev build-essential libssl-dev \ + git-lfs + + - name: Toolchain workaround (GCC 14) + run: | + sudo apt-get install -y gcc-14 g++-14 + echo "CC=gcc-14" >> "$GITHUB_ENV" + echo "CXX=g++-14" >> "$GITHUB_ENV" + + - name: Python Dependencies + id: python_depends + run: | + export PIP_BREAK_SYSTEM_PACKAGES="1" + python3 -m pip install --upgrade pip setuptools + pip3 install ./gguf-py + + - name: Swap Endianness + id: endianness + run: | + for f in models/*.gguf; do + echo YES | python3 gguf-py/gguf/scripts/gguf_convert_endian.py $f big + done + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + time cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Test llama2c (s390x) + id: llama2c_test_s390x + run: | + cd build + echo "Fetch llama2c big-endian model" + wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf + ./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + + ubuntu-24-ppc64le: + runs-on: ubuntu-24.04-ppc64le + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Build Dependencies + id: build_depends + run: | + sudo apt-get update + sudo apt-get install -y --no-install-recommends \ + python3 python3-pip python3-dev python3-wheel \ + libjpeg-dev build-essential libssl-dev \ + git-lfs + + - name: Toolchain workaround (GCC 14) + run: | + sudo apt-get install -y gcc-14 g++-14 + echo "CC=gcc-14" >> "$GITHUB_ENV" + echo "CXX=g++-14" >> "$GITHUB_ENV" + + - name: Python Dependencies + id: python_depends + run: | + export PIP_BREAK_SYSTEM_PACKAGES="1" + python3 -m pip install --upgrade pip setuptools + pip3 install ./gguf-py + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DLLAMA_FATAL_WARNINGS=ON \ + -DGGML_RPC=ON + time cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 diff --git a/.github/workflows/build-opencl.yml b/.github/workflows/build-opencl.yml new file mode 100644 index 000000000..0f8cbe0fc --- /dev/null +++ b/.github/workflows/build-opencl.yml @@ -0,0 +1,83 @@ +name: CI (opencl) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build-opencl.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cl' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-opencl.yml', + 'ggml/src/ggml-opencl/**' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + +jobs: + + windows-latest-opencl-adreno: + runs-on: windows-2025 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: windows-latest-llvm-arm64-opencl-adreno + variant: ccache + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: Install OpenCL Headers and Libs + id: install_opencl + run: | + git clone https://github.com/KhronosGroup/OpenCL-Headers + cd OpenCL-Headers + cmake -B build ` + -DBUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_TESTING=OFF ` + -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build --target install + git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader + cd OpenCL-ICD-Loader + cmake -B build-arm64-release ` + -A arm64 ` + -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` + -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" + cmake --build build-arm64-release --target install --config release + + - name: Build + id: cmake_build + run: | + cmake -S . -B build -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON -DLLAMA_BUILD_BORINGSSL=ON + cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} diff --git a/.github/workflows/build-riscv.yml b/.github/workflows/build-riscv.yml index b78b13140..b5bf84296 100644 --- a/.github/workflows/build-riscv.yml +++ b/.github/workflows/build-riscv.yml @@ -34,6 +34,76 @@ env: LLAMA_LOG_TIMESTAMPS: 1 jobs: + ubuntu-cpu-riscv64-native: + runs-on: ubuntu-24.04-riscv + + steps: + - name: Install dependencies + run: | + # Install necessary packages + sudo apt-get update + sudo apt-get install -y libssl-dev + + # Set gcc-14 and g++-14 as the default compilers + sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100 + sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100 + + git lfs install + + - name: Check environment + run: | + uname -a + gcc --version + g++ --version + ldd --version + cmake --version + rustc --version + + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1 + with: + key: ubuntu-cpu-riscv64-native + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -DCMAKE_BUILD_TYPE=Release \ + -DGGML_OPENMP=OFF \ + -DLLAMA_BUILD_EXAMPLES=ON \ + -DLLAMA_BUILD_TOOLS=ON \ + -DLLAMA_BUILD_TESTS=ON \ + -DCMAKE_C_COMPILER_LAUNCHER=ccache \ + -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ + -DGGML_RPC=ON \ + -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \ + -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 + + time cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + - name: Test llama2c conversion + id: llama2c_test + run: | + cd build + echo "Fetch tokenizer" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin + echo "Fetch llama2c model" + wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin + ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf + ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + ubuntu-riscv64-native-sanitizer: runs-on: ubuntu-24.04-riscv diff --git a/.github/workflows/build-rpc.yml b/.github/workflows/build-rpc.yml new file mode 100644 index 000000000..3c52d7e96 --- /dev/null +++ b/.github/workflows/build-rpc.yml @@ -0,0 +1,67 @@ +name: CI (rpc) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build-rpc.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-rpc.yml', + 'ggml/src/ggml-rpc/**' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + +jobs: + + ubuntu-latest-rpc: + runs-on: ubuntu-latest + + continue-on-error: true + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libssl-dev ninja-build + + - name: Build + id: cmake_build + run: | + cmake -B build \ + -G "Ninja" \ + -DCMAKE_BUILD_TYPE=Release \ + -DGGML_RPC=ON + time cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose diff --git a/.github/workflows/build-sycl.yml b/.github/workflows/build-sycl.yml index 09635f64e..a06030bbb 100644 --- a/.github/workflows/build-sycl.yml +++ b/.github/workflows/build-sycl.yml @@ -38,12 +38,10 @@ jobs: ubuntu-24-sycl: strategy: matrix: - build: [fp32, fp16] + build: [fp32] include: - build: fp32 fp16: OFF - - build: fp16 - fp16: ON runs-on: ubuntu-24.04 diff --git a/.github/workflows/build-webgpu.yml b/.github/workflows/build-webgpu.yml new file mode 100644 index 000000000..2b75027b8 --- /dev/null +++ b/.github/workflows/build-webgpu.yml @@ -0,0 +1,186 @@ +name: CI (webgpu) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build-webgpu.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.wgsl' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-webgpu.yml', + 'ggml/src/ggml-webgpu/**' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + GGML_NLOOP: 3 + GGML_N_THREADS: 1 + LLAMA_LOG_COLORS: 1 + LLAMA_LOG_PREFIX: 1 + LLAMA_LOG_TIMESTAMPS: 1 + +jobs: + + macOS-latest-arm64-webgpu: + runs-on: macos-latest + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: macOS-latest-arm64-webgpu + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dawn Dependency + id: dawn-depends + run: | + DAWN_VERSION="v20260317.182325" + DAWN_OWNER="google" + DAWN_REPO="dawn" + DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release" + echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" + curl -L -o artifact.tar.gz \ + "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" + mkdir dawn + tar -xvf artifact.tar.gz -C dawn --strip-components=1 + + - name: Build + id: cmake_build + run: | + export CMAKE_PREFIX_PATH=dawn + cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF + time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) + + - name: Test + id: cmake_test + run: | + cd build + ctest -L main --verbose --timeout 900 + + ubuntu-24-webgpu: + runs-on: ubuntu-24.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ubuntu-24-webgpu + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo add-apt-repository -y ppa:kisak/kisak-mesa + sudo apt-get update -y + sudo apt-get install -y build-essential mesa-vulkan-drivers \ + libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev + + - name: Get latest Vulkan SDK version + id: vulkan_sdk_version + run: | + echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV" + + - name: Use Vulkan SDK Cache + uses: actions/cache@v5 + id: cache-sdk + with: + path: ./vulkan_sdk + key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }} + + - name: Setup Vulkan SDK + if: steps.cache-sdk.outputs.cache-hit != 'true' + uses: ./.github/actions/linux-setup-vulkan + with: + path: ./vulkan_sdk + version: ${{ env.VULKAN_SDK_VERSION }} + + - name: Dawn Dependency + id: dawn-depends + run: | + sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev + DAWN_VERSION="v20260317.182325" + DAWN_OWNER="google" + DAWN_REPO="dawn" + DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release" + echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" + curl -L -o artifact.tar.gz \ + "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" + mkdir dawn + tar -xvf artifact.tar.gz -C dawn --strip-components=1 + + - name: Build + id: cmake_build + run: | + export Dawn_DIR=dawn/lib64/cmake/Dawn + cmake -B build \ + -DGGML_WEBGPU=ON + time cmake --build build --config Release -j $(nproc) + + - name: Test + id: cmake_test + run: | + cd build + # This is using llvmpipe and runs slower than other backends + # test-backend-ops is too slow on llvmpipe, skip it + ctest -L main -E test-backend-ops --verbose --timeout 900 + + ubuntu-24-webgpu-wasm: + runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }} + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Install Emscripten + run: | + git clone https://github.com/emscripten-core/emsdk.git + cd emsdk + ./emsdk install latest + ./emsdk activate latest + + - name: Fetch emdawnwebgpu + run: | + DAWN_TAG="v20260317.182325" + EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip" + echo "Downloading ${EMDAWN_PKG}" + curl -L -o emdawn.zip \ + "https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}" + unzip emdawn.zip + + - name: Build WASM WebGPU + run: | + source emsdk/emsdk_env.sh + emcmake cmake -B build-wasm \ + -G "Ninja" \ + -DCMAKE_BUILD_TYPE=Release \ + -DGGML_WEBGPU=ON \ + -DLLAMA_OPENSSL=OFF \ + -DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg + + time cmake --build build-wasm --config Release --target test-backend-ops -j $(nproc) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 47b377ff7..ca3fd00fd 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -132,47 +132,6 @@ jobs: cd build ctest -L main --verbose --timeout 900 - macOS-latest-arm64-webgpu: - runs-on: macos-latest - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.21 - with: - key: macOS-latest-arm64-webgpu - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Dawn Dependency - id: dawn-depends - run: | - DAWN_VERSION="v20260317.182325" - DAWN_OWNER="google" - DAWN_REPO="dawn" - DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release" - echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - curl -L -o artifact.tar.gz \ - "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - mkdir dawn - tar -xvf artifact.tar.gz -C dawn --strip-components=1 - - - name: Build - id: cmake_build - run: | - export CMAKE_PREFIX_PATH=dawn - cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF - time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) - - - name: Test - id: cmake_test - run: | - cd build - ctest -L main --verbose --timeout 900 - ubuntu-cpu: strategy: matrix: @@ -181,10 +140,6 @@ jobs: os: ubuntu-22.04 - build: 'arm64' os: ubuntu-24.04-arm - - build: 's390x' - os: ubuntu-24.04-s390x - - build: 'ppc64le' - os: ubuntu-24.04-ppc64le runs-on: ${{ matrix.os }} @@ -194,7 +149,6 @@ jobs: uses: actions/checkout@v6 - name: ccache - if: ${{ matrix.build != 's390x' && matrix.build != 'ppc64le' }} uses: ggml-org/ccache-action@v1.2.21 with: key: ubuntu-cpu-${{ matrix.build }} @@ -224,14 +178,6 @@ jobs: python3 -m pip install --upgrade pip setuptools pip3 install ./gguf-py - - name: Swap Endianness - id: endianness - if: ${{ matrix.build == 's390x' }} - run: | - for f in models/*.gguf; do - echo YES | python3 gguf-py/gguf/scripts/gguf_convert_endian.py $f big - done - - name: Build id: cmake_build run: | @@ -248,7 +194,6 @@ jobs: - name: Test llama2c conversion id: llama2c_test - if: ${{ matrix.build != 's390x' }} run: | cd build echo "Fetch tokenizer" @@ -258,96 +203,6 @@ jobs: ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 - - name: Test llama2c (s390x) - id: llama2c_test_s390x - if: ${{ matrix.build == 's390x' }} - run: | - cd build - echo "Fetch llama2c big-endian model" - 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 - - continue-on-error: true - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libssl-dev ninja-build - - - name: Build - id: cmake_build - run: | - cmake -B build \ - -G "Ninja" \ - -DCMAKE_BUILD_TYPE=Release \ - -DGGML_RPC=ON - time cmake --build build --config Release -j $(nproc) - - - name: Test - id: cmake_test - run: | - cd build - ctest -L main --verbose - ubuntu-24-vulkan: strategy: matrix: @@ -387,176 +242,6 @@ jobs: run: | time cmake --build build -j $(nproc) - ubuntu-24-webgpu: - runs-on: ubuntu-24.04 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.21 - with: - key: ubuntu-24-webgpu - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Dependencies - id: depends - run: | - sudo add-apt-repository -y ppa:kisak/kisak-mesa - sudo apt-get update -y - sudo apt-get install -y build-essential mesa-vulkan-drivers \ - libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev - - - name: Get latest Vulkan SDK version - id: vulkan_sdk_version - run: | - echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV" - - - name: Use Vulkan SDK Cache - uses: actions/cache@v5 - id: cache-sdk - with: - path: ./vulkan_sdk - key: vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }} - - - name: Setup Vulkan SDK - if: steps.cache-sdk.outputs.cache-hit != 'true' - uses: ./.github/actions/linux-setup-vulkan - with: - path: ./vulkan_sdk - version: ${{ env.VULKAN_SDK_VERSION }} - - - name: Dawn Dependency - id: dawn-depends - run: | - sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev - DAWN_VERSION="v20260317.182325" - DAWN_OWNER="google" - DAWN_REPO="dawn" - DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release" - echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - curl -L -o artifact.tar.gz \ - "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - mkdir dawn - tar -xvf artifact.tar.gz -C dawn --strip-components=1 - - - name: Build - id: cmake_build - run: | - export Dawn_DIR=dawn/lib64/cmake/Dawn - cmake -B build \ - -DGGML_WEBGPU=ON - time cmake --build build --config Release -j $(nproc) - - - name: Test - id: cmake_test - run: | - cd build - # This is using llvmpipe and runs slower than other backends - # test-backend-ops is too slow on llvmpipe, skip it - ctest -L main -E test-backend-ops --verbose --timeout 900 - - ubuntu-24-webgpu-wasm: - runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }} - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Install Emscripten - run: | - git clone https://github.com/emscripten-core/emsdk.git - cd emsdk - ./emsdk install latest - ./emsdk activate latest - - - name: Fetch emdawnwebgpu - run: | - DAWN_TAG="v20260317.182325" - EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip" - echo "Downloading ${EMDAWN_PKG}" - curl -L -o emdawn.zip \ - "https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}" - unzip emdawn.zip - - - name: Build WASM WebGPU - run: | - source emsdk/emsdk_env.sh - emcmake cmake -B build-wasm \ - -G "Ninja" \ - -DCMAKE_BUILD_TYPE=Release \ - -DGGML_WEBGPU=ON \ - -DLLAMA_OPENSSL=OFF \ - -DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg - - time cmake --build build-wasm --config Release --target test-backend-ops -j $(nproc) - - ubuntu-22-hip: - runs-on: ubuntu-22.04 - container: rocm/dev-ubuntu-22.04:6.1.2 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev - - - name: ccache - uses: ggml-org/ccache-action@v1.2.21 - with: - key: ubuntu-22-hip - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Build with native CMake HIP support - id: cmake_build - run: | - cmake -B build -S . \ - -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \ - -DGGML_HIP_ROCWMMA_FATTN=ON \ - -DGPU_TARGETS="gfx1030" \ - -DGGML_HIP=ON - cmake --build build --config Release -j $(nproc) - - ubuntu-22-musa: - runs-on: ubuntu-22.04 - container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dependencies - id: depends - run: | - apt-get update - apt-get install -y build-essential git cmake libssl-dev - - - name: ccache - uses: ggml-org/ccache-action@v1.2.21 - with: - key: ubuntu-22-musa - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Build with native CMake MUSA support - id: cmake_build - run: | - cmake -B build -S . \ - -DGGML_MUSA=ON - time cmake --build build --config Release -j $(nproc) - - windows-latest: runs-on: windows-2025 @@ -580,9 +265,6 @@ jobs: - build: 'llvm-arm64' arch: 'arm64' defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON' - - build: 'llvm-arm64-opencl-adreno' - arch: 'arm64' - defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON' steps: - name: Clone @@ -624,26 +306,6 @@ jobs: run: | choco install ninja - - name: Install OpenCL Headers and Libs - id: install_opencl - if: ${{ matrix.build == 'llvm-arm64-opencl-adreno' }} - run: | - git clone https://github.com/KhronosGroup/OpenCL-Headers - cd OpenCL-Headers - cmake -B build ` - -DBUILD_TESTING=OFF ` - -DOPENCL_HEADERS_BUILD_TESTING=OFF ` - -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF ` - -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" - cmake --build build --target install - git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader - cd OpenCL-ICD-Loader - cmake -B build-arm64-release ` - -A arm64 ` - -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" ` - -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release" - cmake --build build-arm64-release --target install --config release - - name: Build id: cmake_build run: | @@ -764,145 +426,6 @@ jobs: cmake --build build --config Release -j %NINJA_JOBS% -t ggml cmake --build build --config Release - - windows-latest-hip: - runs-on: windows-2022 - - env: - # Make sure this is in sync with build-cache.yml - HIPSDK_INSTALLER_VERSION: "26.Q1" - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Grab rocWMMA package - id: grab_rocwmma - run: | - curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb" - 7z x rocwmma.deb - 7z x data.tar - - - name: Use ROCm Installation Cache - uses: actions/cache@v5 - id: cache-rocm - with: - path: C:\Program Files\AMD\ROCm - key: rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }} - - - name: Setup ROCm - if: steps.cache-rocm.outputs.cache-hit != 'true' - uses: ./.github/actions/windows-setup-rocm - with: - version: ${{ env.HIPSDK_INSTALLER_VERSION }} - - - name: Verify ROCm - id: verify - run: | - # Find and test ROCm installation - $clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1 - if (-not $clangPath) { - Write-Error "ROCm installation not found" - exit 1 - } - & $clangPath.FullName --version - - - name: Install ccache - uses: ggml-org/ccache-action@v1.2.21 - with: - key: ${{ github.job }} - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Build - id: cmake_build - run: | - $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path) - $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}" - cmake -G "Unix Makefiles" -B build -S . ` - -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" ` - -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" ` - -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" ` - -DCMAKE_BUILD_TYPE=Release ` - -DLLAMA_BUILD_BORINGSSL=ON ` - -DROCM_DIR="${env:HIP_PATH}" ` - -DGGML_HIP=ON ` - -DGGML_HIP_ROCWMMA_FATTN=ON ` - -DGPU_TARGETS="gfx1100" ` - -DGGML_RPC=ON - cmake --build build -j ${env:NUMBER_OF_PROCESSORS} - - ubuntu-cpu-riscv64-native: - runs-on: ubuntu-24.04-riscv - - steps: - - name: Install dependencies - run: | - # Install necessary packages - sudo apt-get update - sudo apt-get install -y libssl-dev - - # Set gcc-14 and g++-14 as the default compilers - sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100 - sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100 - - git lfs install - - - name: Check environment - run: | - uname -a - gcc --version - g++ --version - ldd --version - cmake --version - rustc --version - - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1 - with: - key: ubuntu-cpu-riscv64-native - evict-old-files: 1d - save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} - - - name: Build - id: cmake_build - run: | - cmake -B build \ - -DCMAKE_BUILD_TYPE=Release \ - -DGGML_OPENMP=OFF \ - -DLLAMA_BUILD_EXAMPLES=ON \ - -DLLAMA_BUILD_TOOLS=ON \ - -DLLAMA_BUILD_TESTS=ON \ - -DCMAKE_C_COMPILER_LAUNCHER=ccache \ - -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ - -DGGML_RPC=ON \ - -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \ - -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 - - time cmake --build build --config Release -j $(nproc) - - - name: Test - id: cmake_test - run: | - cd build - ctest -L main --verbose --timeout 900 - - - name: Test llama2c conversion - id: llama2c_test - run: | - cd build - echo "Fetch tokenizer" - wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin - echo "Fetch llama2c model" - wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin - ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf - ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 - # TODO: simplify the following workflows using a matrix # TODO: run lighter CI on PRs and the full CI only on master (if needed) ggml-ci-x64-cpu-low-perf: diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 54ca22d24..ed88d2471 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -772,12 +772,10 @@ jobs: strategy: matrix: - build: [fp32, fp16] + build: [fp32] include: - build: fp32 fp16: OFF - - build: fp16 - fp16: ON runs-on: ubuntu-24.04 @@ -1363,7 +1361,6 @@ jobs: - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/${{ 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) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp32-x64.tar.gz) - - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp16-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)