All versions · Version range: v0.23.0
In vLLM v0.23.0, vllm:kv_block_idle_before_evict_seconds declares 21 literal histogram bucket boundaries in its registration, from 0.001 to 1800.0.
MetricvLLM v0.23.0confidence: highverified Sep 29verified-code
Metric
kv_block_idle_before_evict_secondsApplies when
PrometheusStatLogger metrics publisherV1 metricsobservability_config.kv_cache_metrics=True
Evidence
vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:974-982)
definesprimarysource_codecode_introspection
974: histogram_kv_block_idle_before_evict = self._histogram_cls( 975: name="vllm:kv_block_idle_before_evict_seconds", 976: documentation=( 977: "Histogram of idle time before KV cache block eviction. " 978: "Sampled metrics (controlled by --kv-cache-metrics-sample)." 979: ), 980: buckets=kv_cache_residency_buckets, 981: labelnames=labelnames, 982: )
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:kv_block_idle_before_evict_seconds