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

vLLM request-completion counter by finish reason

vllm · counter

Fields

id
metric-exposures/w3m-vllm-vllm-request-success
Metric name
vllm:request_success
Metric type
counter
Unit
requests
Exposure
prometheus
Endpoint
:8000/metrics
Labels
model_nameenginefinished_reason
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. The only place a cancelled or length-stopped request is distinguishable.

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. The only place a cancelled or length-stopped request is distinguishable.

Cross-references