In vLLM v0.23.0, vllm:kv_cache_usage_perc is set from SchedulerStats.kv_cache_usage and observes KV-cache usage pressure.
MetricvLLM v0.23.0confidence: highverified 12 min agoverified-code
Metric
kv_cache_usage_percApplies when
V1 scheduler statsPrometheusStatLogger metrics publisher
Evidence
vLLM v0.23.0 v1 metrics stats.py(vllm/v1/metrics/stats.py:171-188)
definesprimarysource_codecode_introspection
vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1081-1081)
definesprimarysource_codecode_introspection
Does not establish
- actual preemption occurrence by itself
- the correct tuning action for a workload
- quantitative benchmark outcomes
Guards
vllm_version= v0.23.0metric_name=vllm:kv_cache_usage_percruntime_component= scheduler