LMDeploy per-request cache-hit-ratio histogram
niche-lmdeploy-turbomind · histogram
Fields
id
metric-exposures/w3m-niche-lmdeploy-turbomind-lmdeploy-request-cache-hit-ratioMetric name
lmdeploy:request_cache_hit_ratio
Metric type
histogram
Unit
1
Exposure
prometheus
Endpoint
:23333/metrics
Histogram buckets
00.10.20.30.40.50.60.70.80.91
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. request_cache_hit_ratio uses an explicit 0.0-1.0 ladder in 0.1 steps.
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. request_cache_hit_ratio uses an explicit 0.0-1.0 ladder in 0.1 steps.