llama.cpp/.github/workflows/build.yml

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

env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
  GGML_NLOOP: 3
  GGML_NITER: 1
  GGML_N_THREADS: 1

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

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

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

      - name: Build
        id: make_build
        run: |
          CC=gcc-8 make

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

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

      - 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 ..
          cmake --build . --config Release

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

  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@v1

      - 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_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
          cmake --build . --config ${{ matrix.build_type }}

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

  macOS-latest-make:
    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: make_build
        run: |
          make

  macOS-latest-cmake:
    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 -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF ..
          cmake --build . --config Release

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

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

    env:
      OPENBLAS_VERSION: 0.3.23
      OPENCL_VERSION: 2023.04.17
      CLBLAST_VERSION: 1.6.0

    strategy:
      matrix:
        include:
          - build: 'avx2'
            defines: '-DLLAMA_BUILD_SERVER=ON'
          - build: 'avx'
            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF'
          - build: 'avx512'
            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
          - build: 'clblast'
            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
          - build: 'openblas'
            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'

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

      - name: Download OpenCL SDK
        id: get_opencl
        if: ${{ matrix.build == 'clblast' }}
        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' }}
        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' }}
        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: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. ${{ matrix.defines }}
          cmake --build . --config Release

      - name: Add clblast.dll
        id: add_clblast_dll
        if: ${{ matrix.build == 'clblast' }}
        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' }}
        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' }}
        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
        if: ${{ matrix.build != 'clblast' && (matrix.build != 'avx512' || env.HAS_AVX512F == '1') }} # Test AVX-512 only when possible
        run: |
          cd build
          ctest -C Release --verbose --timeout 900

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt
          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v3
        with:
          path: |
            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip

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

    strategy:
      matrix:
        cuda: ['12.1.0', '11.7.1']
        build: ['cublas']

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

      - uses: Jimver/cuda-toolkit@v0.2.10
        id: cuda-toolkit
        with:
          cuda: ${{ matrix.cuda }}
          # TODO(green-sky): _dev seems to fail, and non dev are not enought
          #sub-packages: '["nvcc", "cudart", "cublas", "cudart_dev", "cublas_dev"]'

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON
          cmake --build . --config Release

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

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

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v3
        with:
          path: |
            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip

      - name: Copy and pack Cuda runtime
        if: ${{ matrix.cuda == '12.1.0' }}
        # TODO(green-sky): paths are cuda 12 specific
        run: |
          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
          mkdir '.\build\bin\cudart\'
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_12.dll" '.\build\bin\cudart\'
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_12.dll" '.\build\bin\cudart\'
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_12.dll" '.\build\bin\cudart\'
          7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\*

      - name: Copy and pack Cuda runtime
        if: ${{ matrix.cuda == '11.7.1' }}
        # TODO(green-sky): paths are cuda 11 specific
        run: |
          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
          mkdir '.\build\bin\cudart\'
          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin"
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_110.dll" '.\build\bin\cudart\'
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_11.dll" '.\build\bin\cudart\'
          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_11.dll" '.\build\bin\cudart\'
          7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\*

      - name: Upload Cuda runtime
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v3
        with:
          path: |
            cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip

  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-cublas

    steps:
      - name: Download artifacts
        id: download-artifact
        uses: actions/download-artifact@v3

      - name: Get commit hash
        id: commit
        uses: pr-mpt/actions-commit-hash@v2

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

      - 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')) {
              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/${file}`)
                });
              }
            }

#  ubuntu-latest-gcc:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        build: [Debug, Release]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v1
#
#      - 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=${{ matrix.build }}
#
#      - name: Build
#        run: |
#          make
#
#  ubuntu-latest-clang:
#    runs-on: ubuntu-latest
#
#    strategy:
#      matrix:
#        build: [Debug, Release]
#
#    steps:
#      - name: Clone
#        uses: actions/checkout@v1
#
#      - name: Dependencies
#        run: |
#          sudo apt-get update
#          sudo apt-get install build-essential
#          sudo apt-get install cmake
#
#      - name: Configure
#        run: cmake . -DCMAKE_BUILD_TYPE=${{ 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@v1
#
#      - 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@v1
#
#      - 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@v1
#        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@v1
#
#      - 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@v1
#        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@v1
#
#      - 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