https://v0-1.docs.modelplane.ai/guides/Recent content in Guides on Modelplane DocsHugo -- gohugo.ioen-usMon, 01 Jan 0001 00:00:00 +0000https://v0-1.docs.modelplane.ai/guides/collecting-engine-metrics/https://v0-1.docs.modelplane.ai/guides/collecting-engine-metrics/<!-- vale write-good.Passive = NO --> <p>Scraping an inference engine&rsquo;s Prometheus metrics, shown on the smallest serving shape: a 0.5B Qwen chat model on one NVIDIA L4. vLLM publishes metrics at <code>/metrics</code> on its serving port with no extra flag, and Modelplane runs a Prometheus on every workload cluster with <code>PodMonitor</code> discovery open across namespaces, so scraping the engine is a <code>PodMonitor</code> plus a <code>port-forward</code>. The model is only the subject; the same wiring fits any engine, with the SGLang, leader/worker, and prefill/decode differences noted at the end.</p>