[Feature] Metrics Endpoint

[eldhosemjoy]

Motivation

Is there is any endpoint within the API server where we are able to pull the metics like Running Requests
Waiting Requests, Swapped Requests, GPU Cache Usage, CPU Cache Usage, Latency, Prompt Tokens, Generation Tokens?

This is to pull the metrics for the LMDeploy hosted inference engine in to prometheus.

Related resources

No response

Additional context

No response