Schema.ai· vLLM· Schema 0.2.1
vLLM official site vLLM v0.23.0Log in

vllm:request_prefill_kv_computed_tokens

Histogram of new KV tokens computed during prefill, excluding cached tokens.

MetricPrometheusvLLM v0.23.0verified 11 hr ago

Identity

Prometheus type
histogram
Labels
model_nameengine
Buckets
Not recorded — bucket boundaries are computed at runtime from max_model_len, so no fixed values are true
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)

Related Use Cases (1)

Availability

vllm:request_prefill_kv_computed_tokens is registered as a Prometheus histogram 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:920-931