Schema.ai· vLLM
vLLM v0.23.0API up

In vLLM v0.23.0, vllm:prefix_cache_queries is a Prometheus counter measured in queried tokens — it counts tokens, not requests or cache blocks.

MetricvLLM v0.23.0confidence: highverified 4 hr agoverified-code

Metric

prefix_cache_queries

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:542-551)
definesprimarysource_codecode_introspection
vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1083-1088)
supportssecondarysource_codecode_introspection

Does not establish

  • a healthy hit-rate threshold
  • request-level cache behavior (the unit is tokens, not requests)
  • cache sizing guidance

Guards

  • vllm_version = v0.23.0
  • metric_name = vllm:prefix_cache_queries
  • 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.