LLamaSharp/.github/workflows/compile.yml

name: Update Binaries

on:
  workflow_dispatch:
    inputs: {}
  push:
    branches: [cron_job]
  #schedule:
  #  - cron: "22 22 * * 2"

env:
  # Compiler defines common to all platforms
  COMMON_DEFINE: -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_SERVER=OFF -DBUILD_SHARED_LIBS=ON

jobs:
  compile-linux:
    name: Compile (Linux)
    strategy:
      fail-fast: true
      matrix:
        include:
          - build: 'noavx'
            defines: '-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF'
          - build: 'avx2'
            defines: ''
          - build: 'avx'
            defines: '-DLLAMA_AVX2=OFF'
          - build: 'avx512'
            defines: '-DLLAMA_AVX512=ON'
    runs-on: ubuntu-20.04
    steps:
      - uses: actions/checkout@v3
        with:
          repository: ggerganov/llama.cpp
      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. ${{ env.COMMON_DEFINE }} ${{ matrix.defines }}
          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
      - uses: actions/upload-artifact@v3
        with:
          path: ./build/libllama.so
          name: llama-bin-linux-${{ matrix.build }}-x64.so

  compile-windows:
    name: Compile (Windows)
    strategy:
      fail-fast: true
      matrix:
        include:
          - build: 'noavx'
            defines: '-DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF'
          - build: 'avx2'
            defines: ''
          - build: 'avx'
            defines: '-DLLAMA_AVX2=OFF'
          - build: 'avx512'
            defines: '-DLLAMA_AVX512=ON'
    runs-on: windows-latest
    steps:
      - uses: actions/checkout@v3
        with:
          repository: ggerganov/llama.cpp

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

      - name: Upload artifacts
        uses: actions/upload-artifact@v3
        with:
          path: .\build\bin\Release\llama.dll
          name: llama-bin-win-${{ matrix.build }}-x64.dll

  compile-cublas:
    name: Compile (cublas)
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-20.04, windows-latest]
        cuda: ['12.1.0', '11.7.1']
    runs-on: ${{ matrix.os }}
    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          repository: ggerganov/llama.cpp

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

      - uses: Jimver/cuda-toolkit@v0.2.11
        if: runner.os == 'Linux'
        id: cuda-toolkit-linux
        with:
          cuda: ${{ matrix.cuda }}
          method: 'network'
          linux-local-args: '["--toolkit"]'

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_CUBLAS=ON
          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
          ls -R

      - name: Upload artifacts (Windows)
        if: ${{ matrix.os == 'windows-latest' }}
        uses: actions/upload-artifact@v3
        with:
          path: .\build\bin\Release\llama.dll
          name: llama-bin-win-cublas-cu${{ matrix.cuda }}-x64.dll
      - name: Upload artifacts (Linux)
        if: ${{ matrix.os == 'ubuntu-20.04' }}
        uses: actions/upload-artifact@v3
        with:
          path: ./build/libllama.so
          name: llama-bin-linux-cublas-cu${{ matrix.cuda }}-x64.so
    
  compile-macos:
    name: Compile (MacOS)
    strategy:
      fail-fast: true
      matrix:
        include:
          - build: 'arm64'
            defines: '-DCMAKE_OSX_ARCHITECTURES=arm64'
          - build: 'x64'
            defines: '-DCMAKE_OSX_ARCHITECTURES=x86_64 -DLLAMA_METAL=OFF -DLLAMA_AVX=ON -DLLAMA_AVX2=ON'
    runs-on: macos-latest   
    steps:
      - uses: actions/checkout@v3
        with:
          repository: ggerganov/llama.cpp
      - name: Dependencies
        continue-on-error: true
        run: |
          brew update
      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. ${{ env.COMMON_DEFINE }} ${{ matrix.defines }}
          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
      - name: Upload artifacts
        uses: actions/upload-artifact@v3
        with:
          path: ./build/libllama.dylib
          name: llama-bin-osx-${{ matrix.build }}.dylib
      - name: Upload Metal
        if: ${{ matrix.build != 'x64' }}
        uses: actions/upload-artifact@v3
        with:
          path: ./build/bin/ggml-metal.metal
          name: ggml-metal.metal
  
  build-deps:
    runs-on: ubuntu-latest
    name: "Gather Binaries"
    if: ${{ always() }}
    needs: [
      "compile-linux",
      "compile-macos",
      "compile-windows",
      "compile-cublas"
    ]
    steps:      
      - uses: actions/download-artifact@v3
        with:
          path: artifacts
      - name: Rearrange Files
        run: |
          ls -R

          mkdir deps

          mkdir deps/avx
          mkdir deps/avx2
          mkdir deps/avx512

          mkdir deps/osx-arm64
          mkdir deps/osx-x64

          mkdir deps/cu11.7.1
          mkdir deps/cu12.1.0

          cp artifacts/llama-bin-linux-noavx-x64.so/libllama.so  deps/libllama.so
          cp artifacts/llama-bin-linux-avx-x64.so/libllama.so    deps/avx/libllama.so
          cp artifacts/llama-bin-linux-avx2-x64.so/libllama.so   deps/avx2/libllama.so
          cp artifacts/llama-bin-linux-avx512-x64.so/libllama.so deps/avx512/libllama.so

          cp artifacts/llama-bin-win-noavx-x64.dll/llama.dll  deps/libllama.dll
          cp artifacts/llama-bin-win-avx-x64.dll/llama.dll    deps/avx/libllama.dll
          cp artifacts/llama-bin-win-avx2-x64.dll/llama.dll   deps/avx2/libllama.dll
          cp artifacts/llama-bin-win-avx512-x64.dll/llama.dll deps/avx512/libllama.dll

          cp artifacts/llama-bin-osx-arm64.dylib/libllama.dylib deps/osx-arm64/libllama.dylib
          cp artifacts/ggml-metal.metal/ggml-metal.metal        deps/osx-arm64/ggml-metal.metal
          cp artifacts/llama-bin-osx-x64.dylib/libllama.dylib   deps/osx-x64/libllama.dylib

          cp artifacts/llama-bin-win-cublas-cu11.7.1-x64.dll/llama.dll    deps/cu11.7.1/libllama.dll
          cp artifacts/llama-bin-linux-cublas-cu11.7.1-x64.so/libllama.so deps/cu11.7.1/libllama.so
          cp artifacts/llama-bin-win-cublas-cu12.1.0-x64.dll/llama.dll    deps/cu12.1.0/libllama.dll
          cp artifacts/llama-bin-linux-cublas-cu12.1.0-x64.so/libllama.so deps/cu12.1.0/libllama.so

      - name: Upload artifacts
        uses: actions/upload-artifact@v3
        with:
          path: deps/
          name: deps

      - name: Remove Artifacts
        uses: geekyeggo/delete-artifact@v2
        with:
          name: |
            llama-*
            *.metal