94057c3d3e
CI Model Inventory / build-inventory (push) Waiting to run
Lint / lint (push) Waiting to run
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Waiting to run
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Waiting to run
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Waiting to run
PR Benchmark (SMG Components) / Benchmark Summary (push) Blocked by required conditions
Release SGLang Model Gateway Docker Image / publish (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Waiting to run
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Waiting to run
Release SGLang Model Gateway to PyPI / Build SDist (push) Waiting to run
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Blocked by required conditions
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Waiting to run
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Waiting to run
Release SGLang Kernels / release-cu129 (push) Blocked by required conditions
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Waiting to run
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Waiting to run
Release SGLang Kernels / release-cu130 (push) Blocked by required conditions
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Waiting to run
PR Test (SMG) / build-wheel (push) Waiting to run
PR Test (SMG) / python-unit-tests (push) Blocked by required conditions
PR Test (SMG) / unit-tests (push) Waiting to run
PR Test (SMG) / benchmarks (push) Blocked by required conditions
PR Test (SMG) / chat-completions (push) Blocked by required conditions
PR Test (SMG) / chat-completions-4gpu (push) Blocked by required conditions
PR Test (SMG) / e2e (push) Blocked by required conditions
PR Test (SMG) / docker-build-test (push) Waiting to run
PR Test (SMG) / k8s-integration (push) Waiting to run
PR Test (SMG) / finish (push) Blocked by required conditions
PR Test (SMG) / summarize-benchmarks (push) Blocked by required conditions
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Waiting to run
Release SGLang Kernels / release-rocm700 (push) Blocked by required conditions
Release SGLang Kernels / release-rocm720 (push) Blocked by required conditions
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Waiting to run
Release SGLang Kernels / release-musa43 (push) Blocked by required conditions
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
SGLang Monitoring Setup
This directory contains a ready-to-use monitoring setup for SGLang using Prometheus and Grafana.
Prerequisites
- Docker and Docker Compose installed
- SGLang server running with metrics enabled
Usage
- Start your SGLang server with metrics enabled:
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --enable-metrics
By default, the metrics server will run on 127.0.0.1:30000.
- Start the monitoring stack:
cd examples/monitoring
docker compose up
- Access the monitoring interfaces:
- Grafana: http://localhost:3000
- Prometheus: http://localhost:9090
Default Grafana login credentials:
- Username:
admin - Password:
admin
You'll be prompted to change the password on first login.
- The SGLang dashboard will be automatically available in the "SGLang Monitoring" folder.
Troubleshooting
Port Conflicts
If you see errors like "port is already allocated":
-
Check if you already have Prometheus or Grafana running:
docker ps | grep -E 'prometheus|grafana' -
Stop any conflicting containers:
docker stop <container_id> -
Ensure no other services are using ports 9090 and 3000:
lsof -i :9090 lsof -i :3000
Connection Issues
If Grafana cannot connect to Prometheus:
- Check that both services are running
- Verify the datasource configuration in Grafana
- Check that your SGLang server is properly exposing metrics
Configuration
- Prometheus configuration:
prometheus.yaml - Docker Compose configuration:
docker-compose.yaml - Grafana datasource:
grafana/datasources/datasource.yaml - Grafana dashboard configuration:
grafana/dashboards/config/dashboard.yaml - SGLang dashboard JSON:
grafana/dashboards/json/sglang-dashboard.json
Customization
You can customize the monitoring setup by modifying the configuration files as needed.