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 10 hr agoverified-code

Why this matters

Useful for questions about what vllm:num_preemptions counts and when it increments: engine-core events that mark a request preempted increase IterationStats.num_preempted_reqs, which feeds the counter.

Metric

num_preemptions

Applies 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 = v0.23.0
metric_name = vllm:num_preemptions
runtime_component = scheduler

Freshness

Pinned release-tag source snapshot; re-check if target phase-1 release changes or metrics API compatibility becomes customer-facing.