vLLM cumulative preemption counter
vllm · counter
Fields
id
metric-exposures/w3m-vllm-vllm-num-preemptionsMetric name
vllm:num_preemptions
Metric type
counter
Unit
requests
Exposure
prometheus
Endpoint
:8000/metrics
Labels
model_nameengine
Enabled by default
yes
notes
vLLM main, PrometheusStatLogger in vllm/v1/metrics/loggers.py, read 2026-10-04. On by default (EngineArgs.disable_log_stats defaults False); served at :8000/metrics. Bucket family name in --custom-histogram-buckets: no bucket family. 'Cumulative number of preemption from the engine'. This is the engine-lifetime total; the per-request distribution is vllm:request_num_preemptions, a histogram with buckets [1, 2, 3, 4, 5, 10, 20] where the first bucket mixes never-preempted with singly-preempted requests.
Notes
vLLM main, PrometheusStatLogger in vllm/v1/metrics/loggers.py, read 2026-10-04. On by default (EngineArgs.disable_log_stats defaults False); served at :8000/metrics. Bucket family name in --custom-histogram-buckets: no bucket family. 'Cumulative number of preemption from the engine'. This is the engine-lifetime total; the per-request distribution is vllm:request_num_preemptions, a histogram with buckets [1, 2, 3, 4, 5, 10, 20] where the first bucket mixes never-preempted with singly-preempted requests.