The MLServer package exposes a set of methods that let you register and track custom metrics. This can be used within your own custom inference runtimes. To learn more about how to expose custom metrics, check out the metrics usage guide.


Logs a new set of metric values. Each kwarg of this method will be treated as a separate metric / value pair. If any of the metrics does not exist, a new one will be created with a default description.

mlserver.register(name: str, description: str) Histogram

Registers a new metric with its description. If the metric already exists, it will just return the existing one.