[Router][Feat] Add semantic cache to the vLLM router #2
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Router E2E tests | |
| on: | |
| pull_request: | |
| types: [ready_for_review] | |
| paths: | |
| - 'src/vllm_router/**' | |
| - 'docker/**' | |
| - 'setup.py' | |
| workflow_dispatch: | |
| jobs: | |
| e2e-test: | |
| runs-on: ubuntu-latest | |
| if: github.event.pull_request.draft == false | |
| permissions: | |
| contents: read | |
| packages: write | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Setup Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.10.13" | |
| cache: pip | |
| - name: Login to Github Container Registry | |
| uses: docker/login-action@v3 | |
| with: | |
| registry: ghcr.io | |
| username: ${{ github.actor }} | |
| password: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -r src/tests/requirements.txt | |
| pip install -r requirements-test.txt | |
| pip install -e . | |
| - name: Make scripts executable | |
| run: | | |
| chmod +x ./utils/install-minikube-cluster.sh | |
| chmod +x ./utils/install-kubectl.sh | |
| chmod +x ./utils/install-helm.sh | |
| chmod +x src/vllm_router/perf-test.sh | |
| chmod +x src/tests/perftest/*.sh | |
| - name: Setup Test environment | |
| run: | | |
| ./utils/install-minikube-cluster.sh | |
| - name: Build and Load test Image | |
| run: | | |
| REPO=$(echo "${{ github.repository }}" | tr '[:upper:]' '[:lower:]') | |
| docker build -t "ghcr.io/$REPO/router:test" -f docker/Dockerfile . | |
| minikube image load "ghcr.io/$REPO/router:test" | |
| - name: Start Mock OpenAI servers | |
| working-directory: src/tests/perftest | |
| run: | | |
| bash run-multi-server.sh 4 500 | |
| sleep 10 | |
| - name: Start Router for Testing | |
| run: | | |
| bash src/vllm_router/perf-test.sh 8000 & | |
| sleep 5 | |
| - name: Run Performance tests | |
| working-directory: src/tests/perftest | |
| env: | |
| PYTHONPATH: ${{ github.workspace }} | |
| run: | | |
| echo "PYTHONPATH=$PYTHONPATH" | |
| mkdir -p logs | |
| if [ ! -f "request_generator.py" ]; then | |
| echo "Error: request_generator.py not found!" | |
| exit 1 | |
| fi | |
| # Run with Python debug option | |
| python3 -v request_generator.py --qps 10 --num-workers 32 --duration 300 2>&1 | tee logs/request_generator.log | |
| - name: Run E2E Tests | |
| run: | | |
| pytest src/tests/test_*.py | |
| - name: Cleanup Test Environment | |
| if: always() | |
| working-directory: src/tests/perftest | |
| run: | | |
| bash clean-up.sh | |
| - name: Upload Test logs | |
| if: always() | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: test-logs-pr-${{ github.event.pull_request.number || 'manual' }} | |
| path: | | |
| ~/.kube/config | |
| /tmp/minikube.log | |
| src/tests/perftest/logs |