LMDeploy time-to-first-token histogram
niche-lmdeploy-turbomind · histogram
Fields
id
metric-exposures/w3m-niche-lmdeploy-turbomind-lmdeploy-time-to-first-token-secondMetric name
lmdeploy:time_to_first_token_seconds
Metric type
histogram
Unit
seconds
Exposure
prometheus
Endpoint
:23333/metrics
Histogram buckets
0.0010.0050.010.020.040.060.080.10.250.50.7512.557.5102040801606402560
Labels
model_nameengine
Enabled by default
yes
Phase scoped
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. Bucket list is byte-identical to vLLM's TTFT family, which is the clearest evidence this is a direct port rather than a reimplementation. Observed in record_iteration() from stats.ttft.
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. Bucket list is byte-identical to vLLM's TTFT family, which is the clearest evidence this is a direct port rather than a reimplementation. Observed in record_iteration() from stats.ttft.