All versions · Version range: v0.23.0

In vLLM v0.23.0, `vllm:iteration_tokens_total` declares 13 literal histogram bucket boundaries in its registration, from 1.0 to 16384.0.

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

Metric

iteration_tokens_total

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:711-716)

definesprimarysource_codecode_introspection

Open cited lines in immutable upstream source ↗

711:         histogram_iteration_tokens = self._histogram_cls(
712:             name="vllm:iteration_tokens_total",
713:             documentation="Histogram of number of tokens per engine_step.",
714:             buckets=[1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192, 16384],
715:             labelnames=labelnames,
716:         )

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:iteration_tokens_total

Freshness

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