The vLLM v0.23.0 metrics design docs state the metric of interest is the prefix cache hit rate (hits per query): the counters are exposed raw so operators compute the rate over an interval of their choosing with PromQL (rate(hits)/rate(queries)); vLLM's own logging equivalent aggregates hit_rate over the most recent queries.

Metric

Applies when

Evidence

Does not establish

• a healthy or target hit rate (workload-dependent)
• how to increase hit rate for a given workload

Guards

• vllm_version = v0.23.0
• metric_name = vllm:prefix_cache_hits
• runtime_component = kv_cache

Freshness

Pinned release-tag source snapshot; re-check if target phase-1 release changes or metrics API compatibility becomes customer-facing.