name: CI

on:
  workflow_dispatch: # allows manual triggering
    inputs:
      create_release:
        description: 'Create new release'
        required: true
        type: boolean
  push:
    branches:
      - master
    paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal']
  pull_request:
    types: [opened, synchronize, reopened]
    paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal']

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
  cancel-in-progress: true

# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
  contents: write # for creating release

env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_LOG_COLORS: 1
  LLAMA_LOG_PREFIX: 1
  LLAMA_LOG_TIMESTAMPS: 1

jobs:
  macOS-latest-cmake-arm64:
    runs-on: macos-14

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake .. \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_CURL=ON \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DGGML_RPC=ON \
            -DBUILD_SHARED_LIBS=OFF
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L 'main|curl' --verbose --timeout 900

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip
          name: llama-bin-macos-arm64.zip

  macOS-latest-cmake-x64:
    runs-on: macos-13

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          # Metal is disabled due to intermittent failures with Github runners not having a GPU:
          # https://github.com/ggerganov/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
          cmake -B build \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_CURL=ON \
            -DGGML_METAL=OFF \
            -DGGML_RPC=ON \
            -DBUILD_SHARED_LIBS=OFF
          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip
          name: llama-bin-macos-x64.zip

  ubuntu-latest-cmake:
    runs-on: ubuntu-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential libcurl4-openssl-dev

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF
          cmake --build . --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L 'main|curl' --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-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.zip
          name: llama-bin-ubuntu-x64.zip

  ubuntu-latest-cmake-sanitizer:
    runs-on: ubuntu-latest

    continue-on-error: true

    strategy:
      matrix:
        sanitizer: [ADDRESS, THREAD, UNDEFINED]
        build_type: [Debug, Release]

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        if: ${{ matrix.sanitizer != 'THREAD' }}
        run: |
          mkdir build
          cd build
          cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
          cmake --build . --config ${{ matrix.build_type }} -j $(nproc)

      - name: Build (no OpenMP)
        id: cmake_build_no_openmp
        if: ${{ matrix.sanitizer == 'THREAD' }}
        run: |
          mkdir build
          cd build
          cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} -DGGML_OPENMP=OFF
          cmake --build . --config ${{ matrix.build_type }} -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  ubuntu-latest-cmake-rpc:
    runs-on: ubuntu-latest

    continue-on-error: true

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake -DGGML_RPC=ON ..
          cmake --build . --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose

  ubuntu-22-cmake-vulkan:
    runs-on: ubuntu-22.04

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add -
          sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list
          sudo apt-get update -y
          sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake -DGGML_VULKAN=ON ..
          cmake --build . --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  ubuntu-22-cmake-hip:
    runs-on: ubuntu-22.04
    container: rocm/dev-ubuntu-22.04:6.0.2

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev

      - name: Build with native CMake HIP support
        id: cmake_build
        run: |
          cmake -B build -S . -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" -DGGML_HIP=ON
          cmake --build build --config Release -j $(nproc)

      - name: Build with legacy HIP support
        id: cmake_build_legacy_hip
        run: |
          cmake -B build2 -S . -DCMAKE_C_COMPILER=hipcc -DCMAKE_CXX_COMPILER=hipcc -DGGML_HIP=ON
          cmake --build build2 --config Release -j $(nproc)

  ubuntu-22-cmake-musa:
    runs-on: ubuntu-22.04
    container: mthreads/musa:rc3.1.0-devel-ubuntu22.04

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          apt-get update
          apt-get install -y build-essential git cmake libcurl4-openssl-dev

      - name: Build with native CMake MUSA support
        id: cmake_build
        run: |
          cmake -B build -S . -DGGML_MUSA=ON
          cmake --build build --config Release -j $(nproc)

  ubuntu-22-cmake-sycl:
    runs-on: ubuntu-22.04

    continue-on-error: true

    steps:
      - uses: actions/checkout@v4

      - name: add oneAPI to apt
        shell: bash
        run: |
          cd /tmp
          wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main"

      - name: install oneAPI dpcpp compiler
        shell: bash
        run: |
          sudo apt update
          sudo apt install intel-oneapi-compiler-dpcpp-cpp

      - name: install oneAPI MKL library
        shell: bash
        run: |
          sudo apt install intel-oneapi-mkl-devel

      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Build
        id: cmake_build
        run: |
          source /opt/intel/oneapi/setvars.sh
          mkdir build
          cd build
          cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ..
          cmake --build . --config Release -j $(nproc)

  ubuntu-22-cmake-sycl-fp16:
    runs-on: ubuntu-22.04

    continue-on-error: true

    steps:
      - uses: actions/checkout@v4

      - name: add oneAPI to apt
        shell: bash
        run: |
          cd /tmp
          wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
          sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main"

      - name: install oneAPI dpcpp compiler
        shell: bash
        run: |
          sudo apt update
          sudo apt install intel-oneapi-compiler-dpcpp-cpp

      - name: install oneAPI MKL library
        shell: bash
        run: |
          sudo apt install intel-oneapi-mkl-devel

      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Build
        id: cmake_build
        run: |
          source /opt/intel/oneapi/setvars.sh
          mkdir build
          cd build
          cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON ..
          cmake --build . --config Release -j $(nproc)

  # TODO: build with GGML_METAL=OFF because test-backend-ops fail on "Apple Paravirtual device" and I don't know
  #       how to debug it.
  #       ref: https://github.com/ggerganov/llama.cpp/actions/runs/7132125951/job/19422043567?pr=4359#step:5:6584
  #       would be great if we fix these
  macOS-latest-cmake:
    runs-on: macos-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake -DLLAMA_FATAL_WARNINGS=ON -DGGML_METAL=OFF ..
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  macOS-latest-cmake-ios:
    runs-on: macos-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake -G Xcode .. \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_EXAMPLES=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=iOS \
            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO

  macOS-latest-cmake-tvos:
    runs-on: macos-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake -G Xcode .. \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_EXAMPLES=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=tvOS \
            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO

  macOS-latest-swift:
    runs-on: macos-latest

    strategy:
      matrix:
        destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        continue-on-error: true
        run: |
          brew update

      - name: Build llama.cpp with CMake
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake -G Xcode .. \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_EXAMPLES=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
          sudo cmake --install . --config Release

      - name: xcodebuild for swift package
        id: xcodebuild
        run: |
          xcodebuild -scheme llama-Package -destination "${{ matrix.destination }}"

  windows-msys2:
    runs-on: windows-latest

    strategy:
      fail-fast: false
      matrix:
        include:
          - { sys: UCRT64,  env: ucrt-x86_64,  build: Release }
          - { sys: CLANG64, env: clang-x86_64, build: Release }

    steps:
      - name: Clone
        uses: actions/checkout@v4

      - name: Setup ${{ matrix.sys }}
        uses: msys2/setup-msys2@v2
        with:
          update: true
          msystem: ${{matrix.sys}}
          install: >-
            base-devel
            mingw-w64-${{matrix.env}}-toolchain
            mingw-w64-${{matrix.env}}-cmake
            mingw-w64-${{matrix.env}}-openblas

      - name: Build using CMake
        shell: msys2 {0}
        run: |
            cmake -B build
            cmake --build build --config ${{ matrix.build }} -j $(nproc)

      - name: Clean after building using CMake
        shell: msys2 {0}
        run: |
            rm -rf build

      - name: Build using CMake w/ OpenBLAS
        shell: msys2 {0}
        run: |
            cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
            cmake --build build --config ${{ matrix.build }} -j $(nproc)

  windows-latest-cmake:
    runs-on: windows-latest

    env:
      OPENBLAS_VERSION: 0.3.23
      SDE_VERSION: 9.33.0-2024-01-07
      VULKAN_VERSION: 1.3.261.1

    strategy:
      matrix:
        include:
          - build: 'noavx-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DBUILD_SHARED_LIBS=ON'
          - build: 'avx2-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'avx-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_AVX2=OFF -DBUILD_SHARED_LIBS=ON'
          - build: 'avx512-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_AVX512=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'openblas-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BLAS=ON -DBUILD_SHARED_LIBS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
          - build: 'kompute-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'vulkan-x64'
            defines: '-DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_VULKAN=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'llvm-arm64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'msvc-arm64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-msvc.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'llvm-arm64-opencl-adreno'
            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
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Clone Kompute submodule
        id: clone_kompute
        if: ${{ matrix.build == 'kompute-x64' }}
        run: |
          git submodule update --init ggml/src/ggml-kompute/kompute

      - name: Download OpenBLAS
        id: get_openblas
        if: ${{ matrix.build == 'openblas-x64' }}
        run: |
          curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
          curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
          mkdir $env:RUNNER_TEMP/openblas
          tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas
          $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
          $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
          $lib =  $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
          & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll

      - name: Install Vulkan SDK
        id: get_vulkan
        if: ${{ matrix.build == 'kompute-x64' || matrix.build == 'vulkan-x64' }}
        run: |
          curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe"
          & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
          Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
          Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"

      - name: Install Ninja
        id: install_ninja
        run: |
          choco install ninja

      - name: Install OpenCL Headers and Libs
        id: install_opencl
        if: ${{ matrix.build == 'llvm-arm64-opencl-adreno' }}
        run: |
          git clone https://github.com/KhronosGroup/OpenCL-Headers
          cd OpenCL-Headers
          mkdir build && cd build
          cmake .. `
            -DBUILD_TESTING=OFF `
            -DOPENCL_HEADERS_BUILD_TESTING=OFF `
            -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF `
            -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
          cmake --build . --target install
          git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader
          cd OpenCL-ICD-Loader
          mkdir build-arm64-release && cd build-arm64-release
          cmake .. `
            -A arm64 `
            -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" `
            -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
          cmake --build . --target install --config release

      - name: Build
        id: cmake_build
        run: |
          cmake -S . -B build ${{ matrix.defines }}
          cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}

      - name: Add libopenblas.dll
        id: add_libopenblas_dll
        if: ${{ matrix.build == 'openblas-x64' }}
        run: |
          cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
          cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt

      - name: Check AVX512F support
        id: check_avx512f
        if: ${{ matrix.build == 'avx512-x64' }}
        continue-on-error: true
        run: |
          cd build
          $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
          $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
          $cl =  $(join-path $msvc 'bin\Hostx64\x64\cl.exe')
          echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c
          & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main
          .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO"

      - name: Test
        id: cmake_test
        # not all machines have native AVX-512
        if: ${{ matrix.build != 'msvc-arm64' && matrix.build != 'llvm-arm64' && matrix.build != 'llvm-arm64-opencl-adreno' && matrix.build != 'kompute-x64' && matrix.build != 'vulkan-x64' && (matrix.build != 'avx512-x64' || env.HAS_AVX512F == '1') }}
        run: |
          cd build
          ctest -L main -C Release --verbose --timeout 900

      - name: Test (Intel SDE)
        id: cmake_test_sde
        if: ${{ matrix.build == 'avx512-x64' && env.HAS_AVX512F == '0' }} # use Intel SDE for AVX-512 emulation
        run: |
          curl.exe -o $env:RUNNER_TEMP/sde.tar.xz -L "https://downloadmirror.intel.com/813591/sde-external-${env:SDE_VERSION}-win.tar.xz"
          # for some weird reason windows tar doesn't like sde tar.xz
          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar.xz
          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
          $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
          cd build
          $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
          & $sde -future -- ctest -L main -C Release --verbose --timeout 900

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip .\build\bin\Release\*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip
          name: llama-bin-win-${{ matrix.build }}.zip

  ubuntu-latest-cmake-cuda:
    runs-on: ubuntu-latest
    container: nvidia/cuda:12.6.2-devel-ubuntu24.04

    steps:
        - name: Clone
          id: checkout
          uses: actions/checkout@v4

        - name: Install dependencies
          env:
            DEBIAN_FRONTEND: noninteractive
          run: |
              apt update
              apt install -y cmake build-essential ninja-build libgomp1 git

        - name: Build with CMake
          run: |
            cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=89-real -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined -DLLAMA_FATAL_WARNINGS=ON
            cmake --build build

  windows-2019-cmake-cuda:
    runs-on: windows-2019

    strategy:
      matrix:
        cuda: ['12.4', '11.7']
        build: ['cuda']

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
            fetch-depth: 0

      - name: Install Cuda Toolkit 11.7
        if: ${{ matrix.cuda == '11.7' }}
        run: |
          mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
          choco install unzip -y
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip"
          unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
          echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8

      - name: Install Cuda Toolkit 12.4
        if: ${{ matrix.cuda == '12.4' }}
        run: |
          mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
          choco install unzip -y
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip"
          curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip"
          unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
          echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8

      - name: Install ccache
        uses: hendrikmuhs/ccache-action@v1.2
        with:
          key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }}

      - name: Install Ninja
        id: install_ninja
        run: |
          choco install ninja

      - name: Build
        id: cmake_build
        shell: cmd
        run: |
          call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
          cmake -S . -B build -G "Ninja Multi-Config" -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=ON -DGGML_RPC=ON
          set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
          cmake --build build --config Release -j %NINJA_JOBS% -t ggml
          cmake --build build --config Release

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
          name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip

      - name: Copy and pack Cuda runtime
        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
        run: |
          echo "Cuda install location: ${{ env.CUDA_PATH }}"
          $dst='.\build\bin\cudart\'
          robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
          robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
          7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\*

      - name: Upload Cuda runtime
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
          name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip

  windows-latest-cmake-sycl:
    runs-on: windows-latest

    defaults:
      run:
        shell: bash

    env:
      WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe
      WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
      ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Install
        run:  |
          scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL

      - name: Build
        id: cmake_build
        run:  examples/sycl/win-build-sycl.bat

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Build the release package
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin"

          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin

          echo "cp oneAPI running time dll files to ./build/bin done"
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/*

      - name: Upload the release package
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip
          name: llama-bin-win-sycl-x64.zip

  windows-latest-cmake-hip:
    if: ${{ github.event.inputs.create_release != 'true' }}
    runs-on: windows-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Install
        id: depends
        run: |
          $ErrorActionPreference = "Stop"
          write-host "Downloading AMD HIP SDK Installer"
          Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
          write-host "Installing AMD HIP SDK"
          Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait
          write-host "Completed AMD HIP SDK installation"

      - name: Verify ROCm
        id: verify
        run: |
          & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version

      - name: Install ccache
        uses: hendrikmuhs/ccache-action@v1.2
        with:
          key: ${{ github.job }}

      - 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" -DGGML_HIP=ON -DCMAKE_BUILD_TYPE=Release -DGGML_RPC=ON
          cmake --build build -j ${env:NUMBER_OF_PROCESSORS}

  windows-latest-cmake-hip-release:
    if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
    runs-on: windows-latest

    strategy:
      matrix:
        gpu_target: [gfx1100, gfx1101, gfx1030]

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
            fetch-depth: 0

      - name: Install
        id: depends
        run: |
          $ErrorActionPreference = "Stop"
          write-host "Downloading AMD HIP SDK Installer"
          Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
          write-host "Installing AMD HIP SDK"
          Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait
          write-host "Completed AMD HIP SDK installation"

      - name: Verify ROCm
        id: verify
        run: |
          & 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version

      - 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" -DGGML_HIP=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS=${{ matrix.gpu_target }} -DGGML_RPC=ON
          cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
          md "build\bin\rocblas\library\"
          cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\"
          cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\"
          cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\"

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip .\build\bin\*

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-win-hip-x64-${{ matrix.gpu_target }}.zip
          name: llama-bin-win-hip-x64-${{ matrix.gpu_target }}.zip

  ios-xcode-build:
    runs-on: macos-latest

    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake -G Xcode .. \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_EXAMPLES=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=iOS \
            -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
            -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
          sudo cmake --install . --config Release

      - name: xcodebuild for swift package
        id: xcodebuild
        run: |
          xcodebuild -scheme llama-Package -destination 'generic/platform=iOS'

      - name: Build Xcode project
        run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' build

  android-build:
    runs-on: ubuntu-latest

    steps:
      - name: Clone
        uses: actions/checkout@v4

      - name: Set up JDK
        uses: actions/setup-java@v3
        with:
          java-version: 17
          distribution: zulu

      - name: Setup Android SDK
        uses: android-actions/setup-android@v3
        with:
          log-accepted-android-sdk-licenses: false

      - name: Build
        run: |
          cd examples/llama.android

          ./gradlew build --no-daemon

  release:
    if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}

    runs-on: ubuntu-latest

    needs:
      - ubuntu-latest-cmake
      - macOS-latest-cmake
      - windows-latest-cmake
      - windows-2019-cmake-cuda
      - windows-latest-cmake-hip-release
      - macOS-latest-cmake-arm64
      - macOS-latest-cmake-x64

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Download artifacts
        id: download-artifact
        uses: actions/download-artifact@v4
        with:
          path: ./artifact

      - name: Move artifacts
        id: move_artifacts
        run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release

      - name: Create release
        id: create_release
        uses: anzz1/action-create-release@v1
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        with:
          tag_name: ${{ steps.tag.outputs.name }}

      - name: Upload release
        id: upload_release
        uses: actions/github-script@v3
        with:
          github-token: ${{secrets.GITHUB_TOKEN}}
          script: |
            const path = require('path');
            const fs = require('fs');
            const release_id = '${{ steps.create_release.outputs.id }}';
            for (let file of await fs.readdirSync('./artifact/release')) {
              if (path.extname(file) === '.zip') {
                console.log('uploadReleaseAsset', file);
                await github.repos.uploadReleaseAsset({
                  owner: context.repo.owner,
                  repo: context.repo.repo,
                  release_id: release_id,
                  name: file,
                  data: await fs.readFileSync(`./artifact/release/${file}`)
                });
              }
            }

#  ubuntu-latest-gcc:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        build: [Debug, Release]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Dependencies
#        run: |
#          sudo apt-get update
#          sudo apt-get install build-essential
#          sudo apt-get install cmake
#
#      - name: Configure
#        run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }}
#
#      - name: Build
#        run: |
#          make
#
#  ubuntu-latest-clang:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        build: [Debug, Release]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Dependencies
#        run: |
#          sudo apt-get update
#          sudo apt-get install build-essential
#          sudo apt-get install cmake
#
#      - name: Configure
#        run: cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang
#
#      - name: Build
#        run: |
#          make
#
#  ubuntu-latest-gcc-sanitized:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        sanitizer: [ADDRESS, THREAD, UNDEFINED]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Dependencies
#        run: |
#          sudo apt-get update
#          sudo apt-get install build-essential
#          sudo apt-get install cmake
#
#      - name: Configure
#        run: cmake . -DCMAKE_BUILD_TYPE=Debug -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON
#
#      - name: Build
#        run: |
#          make
#
#  windows:
#    runs-on: windows-latest
#
#    strategy:
#      matrix:
#        build: [Release]
#        arch: [Win32, x64]
#        include:
#          - arch: Win32
#            s2arc: x86
#          - arch: x64
#            s2arc: x64
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Add msbuild to PATH
#        uses: microsoft/setup-msbuild@v1
#
#      - name: Configure
#        run: >
#          cmake -S . -B ./build -A ${{ matrix.arch }}
#          -DCMAKE_BUILD_TYPE=${{ matrix.build }}
#
#      - name: Build
#        run: |
#          cd ./build
#          msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }}
#
#      - name: Upload binaries
#        uses: actions/upload-artifact@v4
#        with:
#          name: llama-bin-${{ matrix.arch }}
#          path: build/bin/${{ matrix.build }}
#
#  windows-blas:
#    runs-on: windows-latest
#
#    strategy:
#      matrix:
#        build: [Release]
#        arch: [Win32, x64]
#        blas: [ON]
#        include:
#          - arch: Win32
#            obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x86.zip
#            s2arc: x86
#          - arch: x64
#            obzip: https://github.com/xianyi/OpenBLAS/releases/download/v0.3.21/OpenBLAS-0.3.21-x64.zip
#            s2arc: x64
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Add msbuild to PATH
#        uses: microsoft/setup-msbuild@v1
#
#      - name: Fetch OpenBLAS
#        if: matrix.blas == 'ON'
#        run: |
#          C:/msys64/usr/bin/wget.exe -qO blas.zip ${{ matrix.obzip }}
#          7z x blas.zip -oblas -y
#          copy blas/include/cblas.h .
#          copy blas/include/openblas_config.h .
#          echo "blasdir=$env:GITHUB_WORKSPACE/blas" >> $env:GITHUB_ENV
#
#      - name: Configure
#        run: >
#          cmake -S . -B ./build -A ${{ matrix.arch }}
#          -DCMAKE_BUILD_TYPE=${{ matrix.build }}
#          -DLLAMA_SUPPORT_OPENBLAS=${{ matrix.blas }}
#          -DCMAKE_LIBRARY_PATH="$env:blasdir/lib"
#
#      - name: Build
#        run: |
#          cd ./build
#          msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }}
#
#      - name: Copy libopenblas.dll
#        if: matrix.blas == 'ON'
#        run: copy "$env:blasdir/bin/libopenblas.dll" build/bin/${{ matrix.build }}
#
#      - name: Upload binaries
#        if: matrix.blas == 'ON'
#        uses: actions/upload-artifact@v4
#        with:
#          name: llama-blas-bin-${{ matrix.arch }}
#          path: build/bin/${{ matrix.build }}
#
#  emscripten:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        build: [Release]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v4
#
#      - name: Dependencies
#        run: |
#          wget -q https://github.com/emscripten-core/emsdk/archive/master.tar.gz
#          tar -xvf master.tar.gz
#          emsdk-master/emsdk update
#          emsdk-master/emsdk install latest
#          emsdk-master/emsdk activate latest
#
#      - name: Configure
#        run: echo "tmp"
#
#      - name: Build
#        run: |
#          pushd emsdk-master
#          source ./emsdk_env.sh
#          popd
#          emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }}
#          make