chore: vendor sglang v0.5.10 snapshot

third_party/sglang/.github/workflows/pr-test-rust.yml

@@ -0,0 +1,359 @@
+name: PR Test (SMG)
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - "sgl-model-gateway/**"
+  pull_request:
+    branches: [ main ]
+    types: [opened, synchronize, reopened, labeled]
+    paths:
+      - "sgl-model-gateway/**"
+  workflow_dispatch:
+
+concurrency:
+  group: gateway-tests-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  RUSTC_WRAPPER: sccache
+  SCCACHE_GHA_ENABLED: "true"
+  SGLANG_IS_IN_CI: true
+
+jobs:
+  build-wheel:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: 4-gpu-a10
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install rust dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          cache-all-crates: true
+          cache-on-failure: true
+          save-if: true
+
+      - name: Build python binding
+        run: |
+          source "$HOME/.cargo/env"
+          export RUSTC_WRAPPER=sccache
+          cd sgl-model-gateway/bindings/python
+          python3 -m pip install --upgrade pip maturin
+          maturin build --profile ci --features vendored-openssl --out dist
+
+      - name: List built wheel
+        run: ls -lh sgl-model-gateway/bindings/python/dist/
+
+      - name: Upload wheel artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: smg-wheel
+          path: sgl-model-gateway/bindings/python/dist/*.whl
+          retention-days: 1
+
+      - name: Test wheel install
+        run: |
+          pip install sgl-model-gateway/bindings/python/dist/*.whl
+          python3 -c "import sglang_router; print('Python package: OK')"
+          python3 -c "from sglang_router.sglang_router_rs import Router; print('Rust extension: OK')"
+          python3 -m sglang_router.launch_router --help > /dev/null && echo "Entry point: OK"
+
+  python-unit-tests:
+    needs: build-wheel
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: sglang-repo
+
+      - name: Move sgl-model-gateway folder to root
+        run: |
+          mv sglang-repo/sgl-model-gateway/* .
+          rm -rf sglang-repo
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: smg-wheel
+          path: dist/
+
+      - name: Install wheel
+        run: pip install dist/*.whl
+
+      - name: Run Python unit tests
+        run: |
+          cd bindings/python
+          python3 -m pip install pytest pytest-cov pytest-xdist
+          pytest -q tests --cov=sglang_router --cov-config=.coveragerc --cov-report=term-missing --cov-fail-under=80
+
+  unit-tests:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/cuda/ci_install_gateway_dependencies.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+          disable_annotations: true
+
+      - name: Rust cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: sgl-model-gateway
+          shared-key: "rust-cache"
+          cache-all-crates: true
+          cache-on-failure: true
+          save-if: true
+
+      - name: Run lint
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          rustup component add clippy
+          cargo clippy --all-targets --all-features -- -D warnings
+
+      - name: Run fmt
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          rustup component add --toolchain nightly-x86_64-unknown-linux-gnu rustfmt
+          rustup toolchain install nightly --profile minimal
+          cargo +nightly fmt -- --check
+
+      - name: Generate vision golden fixtures
+        run: |
+          pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+
+          pip install transformers pillow numpy scipy
+          pip install transformers pillow numpy
+          cd sgl-model-gateway/
+          python scripts/generate_vision_golden.py
+
+      - name: Run Rust tests
+        timeout-minutes: 20
+        run: |
+          source "$HOME/.cargo/env"
+          cd sgl-model-gateway/
+          cargo test
+
+      - name: Show sccache stats
+        if: always()
+        run: sccache --show-stats
+
+  gateway-e2e:
+    name: ${{ matrix.name }}
+    needs: build-wheel
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: benchmarks
+            timeout: 32
+            test_dirs: "e2e_test/benchmarks"
+            extra_deps: "genai-bench==0.0.3"
+            env_vars: ""
+            reruns: ""
+            upload_benchmarks: true
+            parallel_opts: ""  # No parallel for benchmarks (performance measurement)
+          - name: responses
+            timeout: 45
+            test_dirs: "e2e_test/responses"
+            extra_deps: ""
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            setup_oracle: true
+            setup_brave: true
+            parallel_opts: ""  # Cloud backend tests not compatible with parallel execution
+          - name: e2e
+            timeout: 45
+            test_dirs: "e2e_test/router e2e_test/embeddings"
+            extra_deps: "pytest-parallel py"  # py is required for pytest-parallel with newer pytest
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            parallel_opts: "--workers 1 --tests-per-worker 4"  # Thread-based parallelism
+          - name: chat-completions
+            timeout: 45
+            test_dirs: "e2e_test/chat_completions"
+            extra_deps: ""
+            env_vars: "SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1"
+            reruns: "--reruns 2 --reruns-delay 5"
+            parallel_opts: ""
+    runs-on: 4-gpu-a10
+    timeout-minutes: ${{ matrix.timeout }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install SGLang dependencies
+        run: |
+          sudo --preserve-env=PATH bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Setup Oracle Instant Client
+        if: matrix.setup_oracle
+        run: |
+          sudo apt-get install -y unzip
+          INSTANT_CLIENT_DIR="/home/ubuntu/instant-client"
+          INSTANT_CLIENT_ZIP="instantclient-basic-linux.x64-23.9.0.25.07.zip"
+
+          if [ ! -d "$INSTANT_CLIENT_DIR/instantclient_23_9" ]; then
+            echo "Downloading Oracle Instant Client..."
+            mkdir -p "$INSTANT_CLIENT_DIR"
+            cd "$INSTANT_CLIENT_DIR"
+            wget https://download.oracle.com/otn_software/linux/instantclient/2390000/$INSTANT_CLIENT_ZIP
+            unzip $INSTANT_CLIENT_ZIP
+            rm $INSTANT_CLIENT_ZIP
+          else
+            echo "Oracle Instant Client already exists, skipping download"
+          fi
+
+          echo "LD_LIBRARY_PATH=/home/ubuntu/instant-client/instantclient_23_9:\$LD_LIBRARY_PATH" >> $GITHUB_ENV
+
+      - name: Start Oracle Database
+        if: matrix.setup_oracle
+        run: |
+          docker run -d -p 1521:1521 -e ORACLE_PASSWORD=oracle --name oracle-db gvenzl/oracle-xe:21-slim
+          echo "Starting Oracle DB..."
+
+          # Export Oracle connection environment variables
+          echo "ATP_USER=system" >> $GITHUB_ENV
+          echo "ATP_PASSWORD=oracle" >> $GITHUB_ENV
+          echo "ATP_DSN=localhost:1521/XEPDB1" >> $GITHUB_ENV
+
+      - name: Start Brave MCP Server
+        if: matrix.setup_brave
+        run: |
+          docker run -d --rm \
+            -p 8001:8080 \
+            -e BRAVE_API_KEY \
+            --name brave-search-server \
+            shoofio/brave-search-mcp-sse:1.0.10
+          echo "Starting Brave MCP Server..."
+          sleep 2
+          curl -f --max-time 1 http://localhost:8001/sse > /dev/null 2>&1 && echo "Brave MCP Server is healthy!" || echo "Brave MCP Server responded"
+
+      - name: Download wheel artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: smg-wheel
+          path: wheel/
+
+      - name: Install wheel
+        run: |
+          pip uninstall -y sglang-router || true
+          pip install wheel/*.whl
+
+      - name: Install e2e test dependencies
+        run: |
+          python3 -m pip install pytest pytest-rerunfailures httpx openai grpcio grpcio-health-checking numpy
+          if [ -n "${{ matrix.extra_deps }}" ]; then
+            python3 -m pip --no-cache-dir install --upgrade ${{ matrix.extra_deps }}
+          fi
+
+      - name: Run E2E tests
+        run: |
+          python3 python/sglang/cli/killall.py
+          cd sgl-model-gateway
+          ${{ matrix.env_vars }} ROUTER_LOCAL_MODEL_PATH="/home/ubuntu/models" pytest ${{ matrix.reruns }} ${{ matrix.parallel_opts }} ${{ matrix.test_dirs }} -s -vv -o log_cli=true --log-cli-level=INFO
+
+      - name: Upload benchmark results
+        if: matrix.upload_benchmarks && success()
+        uses: actions/upload-artifact@v4
+        with:
+          name: genai-bench-results-all-policies
+          path: sgl-model-gateway/benchmark_**/
+
+      - name: Cleanup Brave MCP Server
+        if: always() && matrix.setup_brave
+        run: |
+          docker stop brave-search-server || true
+          docker rm brave-search-server || true
+
+      - name: Cleanup Oracle Database
+        if: always() && matrix.setup_oracle
+        run: |
+          docker stop oracle-db || true
+          docker rm oracle-db || true
+
+  docker-build-test:
+    if: |
+      github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && contains(github.event.pull_request.labels.*.name, 'run-ci')) ||
+      (github.event.action == 'labeled' && github.event.label.name == 'run-ci')
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image (no push)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: docker/gateway.Dockerfile
+          push: false
+          tags: sgl-model-gateway:test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  finish:
+    needs: [build-wheel, python-unit-tests, unit-tests, gateway-e2e, docker-build-test]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Finish
+        run: echo "This is an empty step to ensure that all jobs are completed."
+
+  summarize-benchmarks:
+    needs: gateway-e2e
+    runs-on: ubuntu-latest
+    if: success()
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Download benchmark results
+      uses: actions/download-artifact@v4
+      with:
+        name: genai-bench-results-all-policies
+
+    - name: Create benchmark summary
+      run: python3 sgl-model-gateway/e2e_test/benchmarks/summarize.py .