examples/observability/dashboards/README.md
This directory contains monitoring dashboard configurations for vLLM, providing comprehensive observability for your vLLM deployments.
We provide dashboards for two popular observability platforms:
All dashboards are provided in native formats that work across different deployment methods:
Both platforms provide equivalent monitoring capabilities:
| Dashboard | Description |
|---|---|
| Performance Statistics | Tracks latency, throughput, and performance metrics |
| Query Statistics | Monitors request volume, query performance, and KPIs |
First, navigate to this example's directory:
cd examples/online_serving/dashboards
Import the JSON directly into the Grafana UI, or use the API:
curl -X POST http://grafana/api/dashboards/db \
-H "Content-Type: application/json" \
-d @grafana/performance_statistics.json
Import via the Perses CLI:
percli apply -f perses/performance_statistics.yaml
For detailed deployment instructions and platform-specific options, see:
When adding new dashboards, please: