[model-gateway] refactor e2e test infrastructure and add router CI (#16513)

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

@@ -323,6 +323,60 @@ jobs:
           docker rm oracle-db || true
 
 
+  router-e2e-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: 4-gpu-a10
+    timeout-minutes: 45
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install rust dependencies
+        run: |
+          bash scripts/ci/ci_install_rust.sh
+
+      - name: Configure sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: "v0.12.0"
+
+      - 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: Install SGLang dependencies
+        run: |
+          sudo --preserve-env=PATH bash scripts/ci/ci_install_dependency.sh
+
+      - name: Build python binding
+        run: |
+          source "$HOME/.cargo/env"
+          export RUSTC_WRAPPER=sccache
+          cd sgl-model-gateway/bindings/python
+          python3 -m pip install --upgrade pip maturin
+          pip uninstall -y sglang-router
+          maturin build --profile ci --features vendored-openssl --out dist
+          pip install dist/*.whl
+
+      - name: Install e2e test dependencies
+        run: |
+          python3 -m pip install pytest pytest-rerunfailures httpx openai grpcio grpcio-health-checking
+
+      - name: Run router e2e tests
+        run: |
+          bash scripts/killall_sglang.sh "nuk_gpus"
+          cd sgl-model-gateway
+          source "$HOME/.cargo/env"
+          ROUTER_LOCAL_MODEL_PATH="/home/ubuntu/models" SHOW_WORKER_LOGS=0 SHOW_ROUTER_LOGS=1 pytest --reruns 2 --reruns-delay 5 e2e_test/router -s -vv -o log_cli=true --log-cli-level=INFO
+
   docker-build-test:
     if: |
       github.event_name != 'pull_request' ||
@@ -347,7 +401,7 @@ jobs:
           cache-to: type=gha,mode=max
 
   finish:
-    needs: [maturin-build-test, router-unit-tests, router-http-tests, router-grpc-response-api-tests, docker-build-test]
+    needs: [maturin-build-test, router-unit-tests, router-http-tests, router-grpc-response-api-tests, router-e2e-tests, docker-build-test]
     runs-on: ubuntu-latest
     steps:
       - name: Finish