name: E2E Test

on:
  push:
    branches: [ main ]
    paths:
      - "python/sglang/**"
      - "test/**"
  pull_request:
    branches: [ main ]
    paths:
      - "python/sglang/**"
      - "test/**"
  workflow_dispatch:

concurrency:
  group: e2e-test-${{ github.ref }}
  cancel-in-progress: true

jobs:
  e2e-test:
    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
    runs-on: e2e

    steps:
    - name: Checkout code
      uses: actions/checkout@v3

    - name: Install dependencies
      run: |
        source $HOME/venv/bin/activate
        echo "$HOME/venv/bin" >> $GITHUB_PATH

        pip install --upgrade pip
        pip install -e "python[all]"
        pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall

    - name: Benchmark Serving Throughput
      run: |
        cd test/srt
        python3 -m unittest test_serving_throughput.TestServingThroughput.test_default
      timeout-minutes: 10

    - name: Benchmark Serving Throughput (w/o RadixAttention)
      run: |
        cd test/srt
        python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_radix_cache
      timeout-minutes: 10

    - name: Benchmark Serving Throughput (w/ ChunkedPrefill)
      run: |
        cd test/srt
        python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_with_chunked_prefill
      timeout-minutes: 10