CachyLLama-BUILDER/.github/workflows/build-cachyllama-all.yml

name: Build CachyLLama Multi-Backend Release

on:
  schedule:
    - cron: '0 2 * * *' # Nightly at 2:00 AM UTC
  workflow_dispatch:
    inputs:
      cachyllama_version:
        description: 'CachyLLama branch or tag to build'
        required: false
        default: 'master'
      create_release:
        description: 'Create a GitHub release'
        required: false
        default: true
        type: boolean
  pull_request:
    paths:
      - '.github/workflows/build-cachyllama-all.yml'
      - 'scripts/**'

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

env:
  CACHYLLAMA_VERSION: ${{ github.event.inputs.cachyllama_version || 'master' }}
  CACHYLLAMA_REPO: 'https://github.com/fewtarius/CachyLLama.git'
  CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"

jobs:
  ubuntu-vulkan:
    runs-on: ubuntu-22.04
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y cmake ninja-build libvulkan-dev vulkan-tools glslang-tools glslc build-essential

      - name: Clone CachyLLama
        run: |
          git clone --depth 1 --branch "${{ env.CACHYLLAMA_VERSION }}" "${{ env.CACHYLLAMA_REPO }}" CachyLLama

      - name: Build with Vulkan backend
        run: |
          cd CachyLLama
          cmake -B build -G Ninja \
            -DCMAKE_BUILD_TYPE=Release \
            -DGGML_VULKAN=ON \
            -DGGML_CPU=ON \
            -DGGML_NATIVE=OFF \
            -DCMAKE_INSTALL_RPATH='$ORIGIN' \
            -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(nproc)

      - name: Verify Vulkan Binaries
        run: |
          cd CachyLLama/build/bin
          export LD_LIBRARY_PATH="$(pwd):${LD_LIBRARY_PATH:-}"
          ./llama-cli --help | head -n 10
          ./llama-server --help | head -n 10
          echo "Vulkan binary verification successful!"

      - name: Pack artifacts
        run: |
          cp CachyLLama/LICENSE CachyLLama/build/bin/
          tar -czvf cachy-llama-bin-ubuntu-vulkan-x64.tar.gz -C CachyLLama/build/bin .

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: cachy-llama-bin-ubuntu-vulkan-x64.tar.gz
          path: cachy-llama-bin-ubuntu-vulkan-x64.tar.gz

  ubuntu-cpu:
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
        include:
          - build: 'x64'
            os: ubuntu-22.04
          - build: 'arm64'
            os: ubuntu-24.04-arm
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y cmake ninja-build build-essential

      - name: Clone CachyLLama
        run: |
          git clone --depth 1 --branch "${{ env.CACHYLLAMA_VERSION }}" "${{ env.CACHYLLAMA_REPO }}" CachyLLama

      - name: Build CPU backend
        run: |
          cd CachyLLama
          cmake -B build -G Ninja \
            -DCMAKE_BUILD_TYPE=Release \
            -DGGML_CPU_ALL_VARIANTS=ON \
            -DGGML_NATIVE=OFF \
            -DGGML_OPENMP=ON \
            -DCMAKE_INSTALL_RPATH='$ORIGIN' \
            -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(nproc)

      - name: Pack artifacts
        run: |
          cp CachyLLama/LICENSE CachyLLama/build/bin/
          tar -czvf cachy-llama-bin-ubuntu-cpu-${{ matrix.build }}.tar.gz -C CachyLLama/build/bin .

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: cachy-llama-bin-ubuntu-cpu-${{ matrix.build }}.tar.gz
          path: cachy-llama-bin-ubuntu-cpu-${{ matrix.build }}.tar.gz

  ubuntu-cuda:
    runs-on: ubuntu-22.04
    strategy:
      fail-fast: false
      matrix:
        sm: ${{ github.event_name == 'pull_request' && fromJSON('["89"]') || fromJSON('["75", "80", "86", "89", "90", "100", "120", "121"]') }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Free disk space
        run: |
          sudo apt-get remove -y '^aspnetcore-.*' '^dotnet-.*' '^llvm-.*' 'php.*' 'ruby.*' \
            google-cloud-cli azure-cli google-chrome-stable firefox powershell 2>/dev/null || true
          sudo apt-get autoremove -y
          df -h

      - name: Install CUDA Toolkit
        run: |
          wget -q https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
          sudo dpkg -i cuda-keyring_1.1-1_all.deb
          sudo apt-get update
          sudo apt-get install -y \
            cuda-nvcc-12-8 \
            cuda-cudart-dev-12-8 \
            cuda-cccl-12-8 \
            libcublas-dev-12-8 \
            libcurand-dev-12-8 \
            libnvjitlink-dev-12-8 \
            cmake ninja-build

      - name: Clone CachyLLama
        run: |
          git clone --depth 1 --branch "${{ env.CACHYLLAMA_VERSION }}" "${{ env.CACHYLLAMA_REPO }}" CachyLLama

      - name: Build CUDA backend
        run: |
          export PATH="/usr/local/cuda/bin:$PATH"
          export LD_LIBRARY_PATH="/usr/local/cuda/lib64:${LD_LIBRARY_PATH:-}"
          cd CachyLLama
          cmake -B build -G Ninja \
            -DCMAKE_BUILD_TYPE=Release \
            -DGGML_CUDA=ON \
            -DCMAKE_CUDA_ARCHITECTURES="${{ matrix.sm }}" \
            -DGGML_NATIVE=OFF \
            -DCMAKE_INSTALL_RPATH='$ORIGIN' \
            -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(nproc)

      - name: Verify CUDA Binaries
        run: |
          cd CachyLLama/build/bin
          export LD_LIBRARY_PATH="$(pwd):/usr/local/cuda/lib64:${LD_LIBRARY_PATH:-}"
          ./llama-cli --help | head -n 10
          ./llama-server --help | head -n 10
          echo "CUDA binary verification successful!"

      - name: Pack artifacts
        run: |
          cp CachyLLama/LICENSE CachyLLama/build/bin/
          tar -czvf cachy-llama-bin-ubuntu-cuda-sm_${{ matrix.sm }}-x64.tar.gz -C CachyLLama/build/bin .

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: cachy-llama-bin-ubuntu-cuda-sm_${{ matrix.sm }}-x64.tar.gz
          path: cachy-llama-bin-ubuntu-cuda-sm_${{ matrix.sm }}-x64.tar.gz

  windows-cpu:
    runs-on: windows-2022
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Clone CachyLLama
        shell: powershell
        run: |
          git clone --depth 1 --branch "${{ env.CACHYLLAMA_VERSION }}" "${{ env.CACHYLLAMA_REPO }}" CachyLLama

      - name: Patch CachyLLama for Windows Compatibility
        shell: powershell
        run: |
          python scripts/patch_windows_compat.py CachyLLama

      - name: Build Windows CPU
        shell: cmd
        run: |
          call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
          cd CachyLLama
          cmake -B build -A x64 -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j %NUMBER_OF_PROCESSORS%

      - name: Verify Windows CPU Binaries
        shell: powershell
        run: |
          $binDir = "CachyLLama\build\bin\Release"
          $llamaCli = Join-Path $binDir "llama-cli.exe"
          if (-not (Test-Path $llamaCli)) {
            Write-Error "llama-cli.exe missing!"
            exit 1
          }
          & $llamaCli --help | Select-Object -First 10
          Write-Host "Windows CPU binary verification successful!"

      - name: Pack artifacts
        shell: powershell
        run: |
          Copy-Item CachyLLama\LICENSE CachyLLama\build\bin\Release\
          Compress-Archive -Path CachyLLama\build\bin\Release\* -DestinationPath cachy-llama-bin-windows-cpu-x64.zip

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: cachy-llama-bin-windows-cpu-x64.zip
          path: cachy-llama-bin-windows-cpu-x64.zip

  macos-metal:
    runs-on: macos-14
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Clone CachyLLama
        run: |
          git clone --depth 1 --branch "${{ env.CACHYLLAMA_VERSION }}" "${{ env.CACHYLLAMA_REPO }}" CachyLLama

      - name: Build macOS Metal
        run: |
          cd CachyLLama
          cmake -B build \
            -DCMAKE_BUILD_TYPE=Release \
            -DGGML_METAL=ON \
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3 \
            -DCMAKE_INSTALL_RPATH='@loader_path' \
            -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
            ${{ env.CMAKE_ARGS }}
          cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)

      - name: Verify macOS Metal Binaries
        run: |
          cd CachyLLama/build/bin
          ./llama-cli --help | head -n 10
          ./llama-server --help | head -n 10
          echo "macOS Metal binary verification successful!"

      - name: Pack artifacts
        run: |
          cp CachyLLama/LICENSE CachyLLama/build/bin/
          tar -czvf cachy-llama-bin-macos-metal-arm64.tar.gz -C CachyLLama/build/bin .

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        with:
          name: cachy-llama-bin-macos-metal-arm64.tar.gz
          path: cachy-llama-bin-macos-metal-arm64.tar.gz

  release:
    needs: [ubuntu-vulkan, ubuntu-cpu, ubuntu-cuda, windows-cpu, macos-metal]
    runs-on: ubuntu-22.04
    permissions:
      contents: write
    if: |
      always() &&
      github.event_name != 'pull_request' &&
      (github.event_name == 'schedule' || github.event.inputs.create_release == 'true' || github.event.inputs.create_release == null)
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

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

      - name: Determine tag name
        id: tag
        uses: ./.github/actions/get-tag-name
        with:
          github_token: ${{ secrets.GITHUB_TOKEN }}
          prefix: 'b'

      - name: Prepare release files
        run: |
          mkdir -p ./release-files
          find ./multi-artifacts -type f \( -name "*.tar.gz" -o -name "*.zip" \) -exec cp {} ./release-files/ \;
          ls -la ./release-files/

      - name: Publish GitHub Release
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          TAG="${{ steps.tag.outputs.tag }}"
          gh release create "$TAG" \
            --title "CachyLLama $TAG (Multi-Backend)" \
            --notes "### CachyLLama Multi-Backend Release $TAG
            - **Vulkan RADV**: Linux AMD APU / dGPU acceleration
            - **CPU**: Linux & Windows x64 / ARM64
            - **CUDA**: NVIDIA GPU support (sm_75 to sm_121)
            - **Metal**: Apple Silicon macOS acceleration" \
            ./release-files/*

      - name: Trigger Homebrew Tap Formula Update
        if: success()
        env:
          GITHUB_TOKEN: ${{ secrets.TAP_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
        run: |
          TAG="${{ steps.tag.outputs.tag }}"
          echo "Notifying Homebrew Tap of new release: $TAG"
          gh api -X POST "/repos/Heretek-AI/homebrew-tap/dispatches" \
            -f event_type="builder-release" \
            -f client_payload[builder]="cachyllama" \
            -f client_payload[release_tag]="$TAG" || echo "Note: Tap dispatch triggered or skipped if repo permissions are local"