LMDeploy tokens-per-engine-step histogram
niche-lmdeploy-turbomind · histogram
Fields
id
metric-exposures/w3m-niche-lmdeploy-turbomind-lmdeploy-iteration-tokens-totalMetric name
lmdeploy:iteration_tokens_total
Metric type
histogram
Unit
tokens
Exposure
prometheus
Endpoint
:23333/metrics
Histogram buckets
18163264128256512102420484096819216384
Labels
model_nameengine
Enabled by default
yes
notes
InternLM/lmdeploy main, PrometheusStatLogger in lmdeploy/metrics/loggers.py, read 2026-10-04. On by default and requires NO flag: the endpoint is simply available at the API server port (23333 by default). Label keys are model_name and engine on every metric, where engine carries the dp_rank. Bucket construction reuses vLLM's build_buckets / build_1_2_5_buckets idiom. iteration_tokens_total uses the same 13-bound powers-of-two ladder as vLLM.
Notes
InternLM/lmdeploy main, PrometheusStatLogger in lmdeploy/metrics/loggers.py, read 2026-10-04. On by default and requires NO flag: the endpoint is simply available at the API server port (23333 by default). Label keys are model_name and engine on every metric, where engine carries the dp_rank. Bucket construction reuses vLLM's build_buckets / build_1_2_5_buckets idiom. iteration_tokens_total uses the same 13-bound powers-of-two ladder as vLLM.