All versions · Version range: v0.23.0

In vLLM v0.23.0, `vllm:request_inference_time_seconds` declares 21 literal histogram bucket boundaries in its registration, from 0.3 to 7680.0.

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

Metric

request_inference_time_seconds

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:890-895)

definesprimarysource_codecode_introspection

Open cited lines in immutable upstream source ↗

890:         histogram_inference_time_request = self._histogram_cls(
891:             name="vllm:request_inference_time_seconds",
892:             documentation="Histogram of time spent in RUNNING phase for request.",
893:             buckets=request_latency_buckets,
894:             labelnames=labelnames,
895:         )

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

whether these boundaries suit any particular workload
the distribution of observed values

Guards

vllm_version = v0.23.0
metric_name = vllm:request_inference_time_seconds

Freshness

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