inference/research
verifiedhigh · 0.94updated 2026-10-04

vLLM per-request preemption-count histogram

vllm · histogram

Fields

id
metric-exposures/w3m-vllm-vllm-request-num-preemptions
Metric name
vllm:request_num_preemptions
Metric type
histogram
Unit
requests
Exposure
prometheus
Endpoint
:8000/metrics
Histogram buckets
123451020
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: request_num_preemptions.

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: request_num_preemptions.

Cross-references