name: Tesla K80 Build

on:
  workflow_dispatch: # Manual trigger only

jobs:
  build:
    runs-on: self-hosted

    # Use specific labels if you want to target a particular self-hosted runner
    # runs-on: [self-hosted, linux, cuda, tesla-k80]

    timeout-minutes: 60 # Prevent hung jobs

    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0 # Full history for accurate versioning

      - name: Clean previous build
        run: |
          rm -rf build
          rm -f ollama

      - name: Configure CMake
        run: |
          CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -B build
        env:
          CMAKE_BUILD_TYPE: Release

      - name: Build C++/CUDA components
        run: |
          CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake --build build -j$(nproc)
        timeout-minutes: 30

      - name: Build Go binary
        run: |
          go build -v -o ollama .

      - name: Verify binary was created
        run: |
          ls -lh ollama
          ./ollama --version

      - name: Upload ollama binary and libraries as artifact
        uses: actions/upload-artifact@v4
        with:
          name: ollama-binary
          path: |
            ollama
            build/lib/ollama/
          retention-days: 7