KServe Torchserve Latency

KServe Torchserve Latency Dashobard

<p>Latency metrics for pre/post-process, predict, and explain steps for Torchserve Inference Service with KServe &amp; total number of requests. Requires inferenceservices to use KServe &gt;= v0.10. See <a href="https://kserve.github.io/website/master/modelserving/observability/prometheus_metrics/" target="_blank" rel="noopener noreferrer">KServe observability docs</a> for more info.</p>
Revisions
RevisionDescriptionCreated

Get this dashboard

Import the dashboard template

or

Download JSON

Datasource
Dependencies