llama_cpp/.github/workflows/release.yml

name: Create Release

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

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 }}
  CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"

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

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

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: macOS-latest-cmake-arm64
          evict-old-files: 1d

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

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          cmake -B build \
            -DCMAKE_BUILD_RPATH="@loader_path" \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DGGML_RPC=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)          

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/*          

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip
          name: llama-bin-macos-arm64.zip

  macOS-x64:
    runs-on: macos-13

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

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: macOS-latest-cmake-x64
          evict-old-files: 1d

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

      - 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/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
          cmake -B build \
            -DCMAKE_BUILD_RPATH="@loader_path" \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DGGML_METAL=OFF \
            -DGGML_RPC=ON
          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)          

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/*          

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

  ubuntu-22-cpu:
    strategy:
      matrix:
        include:
          - build: 'x64'
            os: ubuntu-22.04
          - build: 'arm64'
            os: ubuntu-22.04-arm

    runs-on: ${{ matrix.os }}

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

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-cpu-cmake
          evict-old-files: 1d

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

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DLLAMA_FATAL_WARNINGS=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(nproc)          

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/*          

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

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

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

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-22-cmake-vulkan
          evict-old-files: 1d

      - 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 libcurl4-openssl-dev          

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DGGML_VULKAN=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(nproc)          

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          cp LICENSE ./build/bin/
          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/*          

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

  windows:
    runs-on: windows-latest

    env:
      OPENBLAS_VERSION: 0.3.23
      VULKAN_VERSION: 1.4.309.0

    strategy:
      matrix:
        include:
          - build: 'cpu-x64'
            arch: 'x64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF'
          #- build: 'openblas-x64'
          #  arch: 'x64'
          #  defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
          - build: 'vulkan-x64'
            arch: 'x64'
            defines: '-DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
          - build: 'cpu-arm64'
            arch: 'arm64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF'
          - build: 'opencl-adreno-arm64'
            arch: 'arm64'
            defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON'

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

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: windows-latest-cmake-${{ matrix.build }}
          variant: ccache
          evict-old-files: 1d

      - 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 == '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: ${{ matrix.build == 'opencl-adreno-arm64' }}
        run: |
          git clone https://github.com/KhronosGroup/OpenCL-Headers
          cd OpenCL-Headers
          cmake -B build `
            -DBUILD_TESTING=OFF `
            -DOPENCL_HEADERS_BUILD_TESTING=OFF `
            -DOPENCL_HEADERS_BUILD_CXX_TESTS=OFF `
            -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
          cmake --build build --target install
          git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader
          cd OpenCL-ICD-Loader
          cmake -B build-arm64-release `
            -A arm64 `
            -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" `
            -DCMAKE_INSTALL_PREFIX="$env:RUNNER_TEMP/opencl-arm64-release"
          cmake --build build-arm64-release --target install --config release          

      - name: libCURL
        id: get_libcurl
        uses: ./.github/actions/windows-setup-curl
        with:
          architecture: ${{ matrix.arch == 'x64' && 'win64' || 'win64a' }}

      - name: Build
        id: cmake_build
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        run: |
          cmake -S . -B build ${{ matrix.defines }} `
            -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" `
            ${{ env.CMAKE_ARGS }}
          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: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        run: |
          Copy-Item $env:CURL_PATH\bin\libcurl-${{ matrix.arch }}.dll .\build\bin\Release\
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip .\build\bin\Release\*          

      - name: Upload artifacts
        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-cuda:
    runs-on: windows-2019

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

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

      - name: Install ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: windows-cuda-${{ matrix.cuda }}
          variant: ccache
          evict-old-files: 1d

      - name: Install Cuda Toolkit
        uses: ./.github/actions/windows-setup-cuda
        with:
          cuda_version: ${{ matrix.cuda }}

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

      - name: libCURL
        id: get_libcurl
        uses: ./.github/actions/windows-setup-curl

      - name: Build
        id: cmake_build
        shell: cmd
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        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 ^
            -DGGML_BACKEND_DL=ON ^
            -DGGML_CPU_ALL_VARIANTS=ON ^
            -DGGML_CUDA=ON ^
            -DCURL_LIBRARY="%CURL_PATH%/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="%CURL_PATH%/include" ^
            ${{ env.CMAKE_ARGS }}
          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
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        run: |
          cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-cuda${{ matrix.cuda }}-x64.zip .\build\bin\Release\*          

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

      - name: Copy and pack Cuda runtime
        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" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
          7z a cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip $dst\*          

      - name: Upload Cuda runtime
        uses: actions/upload-artifact@v4
        with:
          path: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
          name: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip

  windows-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: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: windows-latest-cmake-sycl
          variant: ccache
          evict-old-files: 1d

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

      # TODO: add libcurl support ; we will also need to modify win-build-sycl.bat to accept user-specified args

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

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Build the release package
        id: pack_artifacts
        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
        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-hip:
    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: Clone rocWMMA repository
        id: clone_rocwmma
        run: |
          git clone https://github.com/rocm/rocwmma --branch rocm-6.2.4 --depth 1          

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: windows-latest-cmake-hip-release
          evict-old-files: 1d

      - 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: libCURL
        id: get_libcurl
        uses: ./.github/actions/windows-setup-curl

      - name: Build
        id: cmake_build
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        run: |
          $env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
          $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
          cmake -G "Unix Makefiles" -B build -S . `
            -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
            -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/rocwmma/library/include/" `
            -DCMAKE_BUILD_TYPE=Release `
            -DAMDGPU_TARGETS=${{ matrix.gpu_target }} `
            -DGGML_HIP_ROCWMMA_FATTN=ON `
            -DGGML_HIP=ON `
            -DCURL_LIBRARY="$env:CURL_PATH/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:CURL_PATH/include" `
            ${{ env.CMAKE_ARGS }}
          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
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        env:
          CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
        run: |
          cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\libcurl-x64.dll
          7z a llama-${{ 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
        with:
          fetch-depth: 0

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          cmake -B build -G Xcode \
            -DGGML_METAL_USE_BF16=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_CURL=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
            -DLLAMA_BUILD_TOOLS=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 build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO          

      - name: xcodebuild for swift package
        id: xcodebuild
        run: |
          ./build-xcframework.sh          

      - 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' FRAMEWORK_FOLDER_PATH=./build-ios build

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Pack artifacts
        id: pack_artifacts
        run: |
          zip --symlinks -r llama-${{ steps.tag.outputs.name }}-xcframework.zip build-apple/llama.xcframework          

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-xcframework.zip
          name: llama-${{ steps.tag.outputs.name }}-xcframework

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

    runs-on: ubuntu-latest

    needs:
      - ubuntu-22-cpu
      - ubuntu-22-vulkan
      - windows
      - windows-cuda
      - windows-sycl
      - windows-hip
      - macOS-arm64
      - macOS-x64

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

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name

      - 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: ggml-org/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}`)
                });
              }
            }