Schema.ai· vLLM
vLLM official site Log in
All versions · Version range: v0.23.0

In vLLM v0.23.0, vllm:num_requests_running is a Prometheus gauge for the number of requests in model execution batches.

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

Metric

num_requests_running

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:451-459)
definesprimarysource_codecode_introspection

Open cited lines in immutable upstream source ↗

451:         gauge_scheduler_running = self._gauge_cls(
452:             name="vllm:num_requests_running",
453:             documentation="Number of requests in model execution batches.",
454:             multiprocess_mode="mostrecent",
455:             labelnames=labelnames,
456:         )
457:         self.gauge_scheduler_running = create_metric_per_engine(
458:             gauge_scheduler_running, per_engine_labelvalues
459:         )

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 value for any workload
  • a recommended threshold for running requests
  • metric stability in later vLLM releases

Guards

  • vllm_version = v0.23.0
  • metric_name = vllm:num_requests_running
  • runtime_component = scheduler

Freshness

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