[Observability] vLLM Prometheus metrics scraping #37

Open
opened 2026-09-11 01:27:24 +00:00 by poimen · 0 comments
Member

Traditional CPU/RAM metrics miss engine queues and frozen users. Scrape vLLM-native /metrics for TTFT, ITL, KV cache usage, queue depth. Gateway already has prometheus annotations (deployment.yaml:30-32) but vLLM pods don't. Add ServiceMonitor for llm-serving namespace. Files: k8s/apps/llm-serving/, k8s/infra/monitoring/

Traditional CPU/RAM metrics miss engine queues and frozen users. Scrape vLLM-native /metrics for TTFT, ITL, KV cache usage, queue depth. Gateway already has prometheus annotations (deployment.yaml:30-32) but vLLM pods don't. Add ServiceMonitor for llm-serving namespace. Files: k8s/apps/llm-serving/, k8s/infra/monitoring/
poimen added this to the LLM Production Hardening milestone 2026-09-11 01:27:24 +00:00
Sign in to join this conversation.