Documentation vLLM

Prometheus and Grafana

A guide to observing vLLM with Prometheus and Grafana.

Grafana dashboard showing vLLM request, token and GPU metrics.
View full preview Original source artwork · vLLM. View in context ↗
  • Inference
  • Observability

In this reference

A guide to observing vLLM with Prometheus and Grafana.

Cite the original work

Prometheus and Grafana [Documentation]. vLLM. https://docs.vllm.ai/en/latest/examples/observability/prometheus_grafana/

View BibTeX
@misc{prometheus_and_grafana,
  title = {{Prometheus and Grafana}},
  howpublished = {vLLM},
  url = {https://docs.vllm.ai/en/latest/examples/observability/prometheus_grafana/}
}
← Back to the library