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/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m']
  pull_request:
    types: [opened, synchronize, reopened]
    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m']

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

env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 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_METAL_EMBED_LIBRARY=ON -DLLAMA_CURL=ON ..
          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-latest

    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
          # 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 -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_METAL=OFF -DLLAMA_CURL=ON ..
          cmake --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-focal-make:
    runs-on: ubuntu-20.04
    env:
      LLAMA_NODE_AVAILABLE: true
      LLAMA_PYTHON_AVAILABLE: 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 gcc-8

      - uses: actions/setup-node@v4
        with:
          node-version: "20"

      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Build
        id: make_build
        env:
            LLAMA_FATAL_WARNINGS: 1
        run: |
          CC=gcc-8 make -j $(nproc)

      - name: Test
        id: make_test
        run: |
          CC=gcc-8 make tests -j $(nproc)
          make test -j $(nproc)

  ubuntu-focal-make-curl:
    runs-on: ubuntu-20.04

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

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential gcc-8 libcurl4-openssl-dev

      - name: Build
        id: make_build
        env:
          LLAMA_FATAL_WARNINGS: 1
          LLAMA_CURL: 1
        run: |
          CC=gcc-8 make -j $(nproc)

  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
          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/convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
          ./bin/main -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
#        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: Test
#        id: cmake_test
#        run: |
#          cd build
#          ctest -L main --verbose --timeout 900

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

    continue-on-error: true

    strategy:
      matrix:
        mpi_library: [mpich, libopenmpi-dev]

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

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential ${{ matrix.mpi_library }}

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

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

  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 -DLLAMA_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: |
          sudo apt-get update
          sudo apt-get install build-essential libvulkan-dev

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

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

    continue-on-error: true

    steps:
      - uses: actions/checkout@v2

      - 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 -DLLAMA_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@v2

      - 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 -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON ..
          cmake --build . --config Release -j $(nproc)

  # TODO: build with LLAMA_NO_METAL 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/7131777249/job/19420981052#step:5:1124
  macOS-latest-make:
    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: make_build
        env:
            LLAMA_FATAL_WARNINGS: 1
        run: |
          LLAMA_NO_METAL=1 make -j $(sysctl -n hw.logicalcpu)

      - name: Test
        id: make_test
        run: |
          LLAMA_NO_METAL=1 make tests -j $(sysctl -n hw.logicalcpu)
          LLAMA_NO_METAL=1 make test  -j $(sysctl -n hw.logicalcpu)

  # TODO: build with LLAMA_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 -DLLAMA_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@v1

      - 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 .. \
            -DLLAMA_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
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)

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

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v1

      - 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 .. \
            -DLLAMA_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
          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)

  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@v1

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

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

      - name: Build Swift Example
        id: make_build_swift_example
        run: |
            make swift

  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 make
        shell: msys2 {0}
        run: |
            make -j $(nproc)

      - name: Clean after building using make
        shell: msys2 {0}
        run: |
            make clean

      - name: Build using make w/ OpenBLAS
        shell: msys2 {0}
        run: |
            make LLAMA_OPENBLAS=1 -j $(nproc)

      - 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 -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
            cmake --build build --config ${{ matrix.build }} -j $(nproc)

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

    env:
      OPENBLAS_VERSION: 0.3.23
      OPENCL_VERSION: 2023.04.17
      CLBLAST_VERSION: 1.6.0
      SDE_VERSION: 9.33.0-2024-01-07
      VULKAN_VERSION: 1.3.261.1

    strategy:
      matrix:
        include:
          - build: 'rpc-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_RPC=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'noavx-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON'
          - build: 'avx2-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'avx-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON'
          - build: 'avx512-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'clblast-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
          - build: 'openblas-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
          - build: 'kompute-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'vulkan-x64'
            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'llvm-arm64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DLLAMA_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 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=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 kompute

      - name: Download OpenCL SDK
        id: get_opencl
        if: ${{ matrix.build == 'clblast-x64' }}
        run: |
          curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip"
          mkdir $env:RUNNER_TEMP/opencl
          tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl

      - name: Download CLBlast
        id: get_clblast
        if: ${{ matrix.build == 'clblast-x64' }}
        run: |
          curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z"
          curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE"
          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z
          rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast
          foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) {
            $txt = Get-Content -Path $f -Raw
            $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8
          }

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

      - name: Add clblast.dll
        id: add_clblast_dll
        if: ${{ matrix.build == 'clblast-x64' }}
        run: |
          cp $env:RUNNER_TEMP/clblast/lib/clblast.dll ./build/bin/Release
          cp $env:RUNNER_TEMP/CLBlast.LICENSE.txt ./build/bin/Release/CLBlast-${env:CLBLAST_VERSION}.txt

      - 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 != 'clblast-x64' && 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
          & $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

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

    strategy:
      matrix:
        cuda: ['12.2.0', '11.7.1']
        build: ['cuda']

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

      - uses: Jimver/cuda-toolkit@v0.2.11
        id: cuda-toolkit
        with:
          cuda: ${{ matrix.cuda }}
          method: 'network'
          sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUDA=ON -DBUILD_SHARED_LIBS=ON
          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}

      - 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
        run: |
          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
          $dst='.\build\bin\cudart\'
          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
          7z a cudart-llama-bin-win-cu${{ 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/7dff44ba-e3af-4448-841c-0d616c8da6e7/w_BaseKit_p_2024.1.0.595_offline.exe
      WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.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: Pack artifacts
        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.4.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 "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/pi_win_proxy_loader.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/pi_level_zero.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl7.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin
          echo "cp oneAPI running time dll files to ./build/bin done"
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/*

      - name: Upload 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-sycl-x64.zip
          name: llama-bin-win-sycl-x64.zip

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

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

      - 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

#  freeBSD-latest:
#    runs-on: macos-12
#    steps:
#    - name: Clone
#      uses: actions/checkout@v4
#
#    - name: Build
#      uses: cross-platform-actions/action@v0.19.0
#      with:
#        operating_system: freebsd
#        version: '13.2'
#        hypervisor: 'qemu'
#        run: |
#            sudo pkg update
#            sudo pkg install -y gmake automake autoconf pkgconf llvm15 clinfo clover opencl clblast openblas
#            gmake CC=/usr/local/bin/clang15 CXX=/usr/local/bin/clang++15 -j `sysctl -n hw.ncpu`

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

    runs-on: ubuntu-latest

    needs:
      - ubuntu-focal-make
      - ubuntu-latest-cmake
      - macOS-latest-make
      - macOS-latest-cmake
      - windows-latest-cmake
      - windows-latest-cmake-cuda
      - 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