In vLLM v0.23.0, `vllm:prefix_cache_hits` is incremented from `SchedulerStats.prefix_cache_stats.hits` on each logging update and observes prefix-cache token reuse for the first-party prefix cache (KV-connector prefix-cache reuse is reported by the separate `vllm:external_prefix_cache_*` counters).

MetricvLLM v0.23.0confidence: highverified 10 min agoverified-code

PrometheusStatLogger metrics publisherV1 metrics

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1083-1088)

definesprimarysource_codecode_introspection

definesprimarysource_codecode_introspection

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:562-588)

supportssecondarysource_codecode_introspection

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

In vLLM v0.23.0, vllm:prefix_cache_hits is incremented from SchedulerStats.prefix_cache_stats.hits on each logging update and observes prefix-cache token reuse for the first-party prefix cache (KV-connector prefix-cache reuse is reported by the separate vllm:external_prefix_cache_* counters).