All versions · Version range: v0.23.0

vllm:prompt_tokens

Counter for the number of prefill tokens processed.

MetricPrometheusverified Sep 29

Version history

In the only version covered here, v0.23.0, vllm:prompt_tokens is registered as a Prometheus counter carrying the label names model_name and engine under the V1 PrometheusStatLogger publisher.
In v0.23.0 it counts prefill tokens processed across iterations, incrementing from IterationStats.num_prompt_tokens during iteration logging.
In v0.23.0 it reflects aggregate prefill work without distinguishing cached from newly computed prompt tokens, so it should be read as a rate for prompt throughput and paired with cached/computed-token and queue/TTFT metrics before drawing efficiency conclusions.

Identity

Prometheus type: counter
Labels: model_nameengine
Unit: Not recorded — vLLM registration code has no structured unit field, and units are not inferred from name suffixes

Semantic coverage

covered · Availability & namecovered · Structural identitycovered · Measurement semanticscovered · Causal/runtime semanticscovered · Interpretation & compositioncovered · Guarded guidance

Metric knowledge (6)

Claim	Semantic layer	Verified
In vLLM v0.23.0, `vllm:prompt_tokens` counts prefill tokens processed across iterations.	Measurement semantics	Sep 29
In vLLM v0.23.0, `vllm:prompt_tokens` increments from `IterationStats.num_prompt_tokens` during iteration logging.	Causal/runtime semantics	Sep 29
In vLLM v0.23.0, `vllm:prompt_tokens` is aggregate prefill work and does not by itself distinguish cached from newly computed prompt tokens.	Interpretation & composition	Sep 29
In vLLM v0.23.0, `vllm:prompt_tokens` use rate for prompt throughput and pair it with cached/computed-token and queue/TTFT metrics before drawing efficiency conclusions.	Guarded guidance	Sep 29
In vLLM v0.23.0, `vllm:prompt_tokens` is registered as a Prometheus counter.	Structural identity	Sep 29
In vLLM v0.23.0, `vllm:prompt_tokens` is registered with the label names `model_name`, engine.	Structural identity	Sep 29

Related Use Cases (1)

#35048: Aggregate throughput can hide experience regressions

Availability

vllm:prompt_tokens is registered as a Prometheus counter in vLLM v0.23.0.

vllm.surface.prometheus_metricscomplete_inventoryPrometheusStatLogger metrics publisher

vLLM v0.23.0 v1 metrics loggers.py · vllm/v1/metrics/loggers.py:628-635