In vLLM v0.23.0, vllm:num_preemptions increments from IterationStats.num_preempted_reqs, which is increased when engine-core events mark requests as preempted.
MetricvLLM v0.23.0confidence: highverified 14 min agoverified-code
Metric
num_preemptionsApplies when
V1 engine-core preemption eventsPrometheusStatLogger metrics publisher
Evidence
vLLM v0.23.0 v1 metrics stats.py(vllm/v1/metrics/stats.py:419-426)
definesprimarysource_codecode_introspection
vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1149-1150)
definesprimarysource_codecode_introspection
Does not establish
- that every preemption is caused by KV cache pressure
- which config knob should be changed
- the operational severity of a given counter value
Guards
vllm_version= v0.23.0metric_name=vllm:num_preemptionsruntime_component= scheduler