Glossary: Serving LLMs at Scale
Histogram
Also written: histogram_quantile
A metric that counts values in buckets (under 0.1 s, under 0.25 s...). PromQL can estimate percentiles from the buckets.
Glossary: Serving LLMs at Scale
Also written: histogram_quantile
A metric that counts values in buckets (under 0.1 s, under 0.25 s...). PromQL can estimate percentiles from the buckets.