build-and-run.yml

name: GPULlama3 Build & Run

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]  
    types: [opened, synchronize, reopened]

env:
  JAVA_HOME: /opt/jenkins/jdks/graal-23.1.0/jdk-21.0.3
  TORNADO_ROOT: ${{ github.workspace }}/GPULlama3.java/external/tornadovm
  LLAMA_ROOT: ${{ github.workspace }}
  GRAAL_JARS: /opt/graalJars
  MODELS_DIR: /opt/models

jobs:
  code-quality:
    if: github.repository == 'beehive-lab/GPULlama3.java'
    runs-on: self-hosted
    timeout-minutes: 30

    steps:
      - name: Checkout GPULlama3
        uses: actions/checkout@v4

      - name: Check code formatting (Spotless)
        run: |
          cd ${{ github.workspace }}
          # ./mvnw -T12C -Pspotless spotless:check

  build-and-run:
    if: github.repository == 'beehive-lab/GPULlama3.java'
    runs-on: [self-hosted]
    needs: code-quality
    timeout-minutes: 30

    strategy:
      fail-fast: true
      matrix:
        backend:
          - name: opencl
          - name: ptx

    steps:
      - name: Checkout GPULlama3
        uses: actions/checkout@v4

      - name: Clone TornadoVM master
        run: |
          git clone --depth 1 --branch master \
            https://github.com/beehive-lab/TornadoVM.git \
            $TORNADO_ROOT
      - name: Set up Python venv for TornadoVM
        run: |
          python3 -m venv $TORNADO_ROOT/venv
          source $TORNADO_ROOT/venv/bin/activate
          python --version
      - name: Build TornadoVM
        run: |
          cd $TORNADO_ROOT
          mkdir -p graalJars && cp $GRAAL_JARS/* graalJars/
          source venv/bin/activate
          echo "=== Building TornadoVM ==="
          
          make BACKEND=${{ matrix.backend.name }}
          
          echo "=== Searching for TornadoVM SDK directory ==="
          SDK_DIR=$(find dist -type d -maxdepth 3 -path "*/tornadovm-*-${{ matrix.backend.name }}" | head -n 1)
          if [ -z "$SDK_DIR" ]; then
            echo "::error::Could not locate TornadoVM SDK directory!"
            find dist -maxdepth 5 -type d
            exit 1
          fi
          FULL_SDK="${PWD}/${SDK_DIR}"
          echo "Detected TornadoVM SDK: $FULL_SDK"
          
          # Export for current shell session
          export TORNADOVM_HOME="$FULL_SDK"
          export PATH="$FULL_SDK/bin:$JAVA_HOME/bin:$PATH"

          # Save for subsequent steps
          echo "TORNADOVM_HOME=$FULL_SDK" >> $GITHUB_ENV
          echo "PATH=$PATH" >> $GITHUB_ENV
          
          echo "=== Checking tornado CLI ==="
          which tornado || { echo "::error::tornado not in PATH"; exit 1; }
          tornado --devices
      - name: Build GPULlama3.java
        run: |
          cd ${{ github.workspace }}
          echo "Using TORNADOVM_HOME=$TORNADOVM_HOME"
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          tornado --version
          ./mvnw clean package -DskipTests
      - name: FP16 - Run Llama-3.2-1B-Instruct-F16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Llama-3.2-1B-Instruct-F16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Qwen3-4B-f16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Qwen3-4B-f16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Mistral-7B-Instruct-v0.3.fp16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Mistral-7B-Instruct-v0.3.fp16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Qwen2.5-1.5b-instruct-fp16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/qwen2.5-1.5b-instruct-fp16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Phi-3-mini-4k-instruct-fp16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model /$MODELS_DIR/Phi-3-mini-4k-instruct-fp16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Granite-3.2-2b-instruct-f16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model /$MODELS_DIR/granite-3.2-2b-instruct-f16.gguf \
            --prompt "Say hello"
      - name: FP16 - Run Granite-4.0-1b-F16.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model /$MODELS_DIR/granite-4.0-1b-F16.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Llama-3.2-1B-Instruct-Q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Llama-3.2-1B-Instruct-Q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Qwen3-0.6B-Q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Qwen3-0.6B-Q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Phi-3-mini-4k-instruct-Q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Phi-3-mini-4k-instruct-Q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Qwen2.5-1.5b-instruct-q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/qwen2.5-1.5b-instruct-q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Mistral-7B-Instruct-v0.3.Q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model $MODELS_DIR/Mistral-7B-Instruct-v0.3.Q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Granite-3.2-2b-instruct-Q8.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model /$MODELS_DIR/granite-3.2-2b-instruct-Q8_0.gguf \
            --prompt "Say hello"
      - name: Q8 - Run Granite-4.0-1b-Q8_0.gguf
        run: |
          cd ${{ github.workspace }}
          export PATH="$TORNADOVM_HOME/bin:$JAVA_HOME/bin:$PATH"
          ./llama-tornado --gpu --${{ matrix.backend.name }} \
            --model /$MODELS_DIR/granite-4.0-1b-Q8_0.gguf \
            --prompt "Say hello"