Use Cases

Use case	What it targets	Questions	Capabilities	vLLM
Prefix cache effectiveness is the derived hit rate, not the exposed counters	The vLLM design docs record prefix-cache activity as two token-denominated counters but state the metric of interest is the derived hit rate. The rationale section never names the real metrics (its PromQL example uses placeholder names), s…	3	retrieval, honesty	v0.23.0
Prometheus exposition names differ from declared metric names	prometheus_client renames samples at exposition: counters gain _total and histograms emit _bucket/_count/_sum series, so the names operators see in scrapes and PromQL differ from the declared registration names. Before 2026-07-15 the _tota…	3	scope, retrieval	v0.23.0