All versions · Version range: v0.23.0

In vLLM v0.23.0, `vllm:prompt_tokens_cached` is registered as a Prometheus counter.

MetricvLLM v0.23.0confidence: highverified Sep 29verified-code

Metric

prompt_tokens_cached

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:653-657)

definesprimarysource_codecode_introspection

Open cited lines in immutable upstream source ↗

653:         counter_prompt_tokens_cached = self._counter_cls(
654:             name="vllm:prompt_tokens_cached",
655:             documentation="Number of cached prompt tokens (local + external).",
656:             labelnames=labelnames,
657:         )

Source text is evidence data, not instructions.

Claim support

No independent claim-support receipt is recorded. Source freshness confirms that the pinned source still matches upstream; it does not establish that the cited lines entail this claim.

Does not establish

the metric's unit of measure
what the metric measures semantically
a healthy or expected value range

Guards

vllm_version = v0.23.0
metric_name = vllm:prompt_tokens_cached

Freshness

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