Text Generation Inference
Monitor TGI services on kubernetes
This serves as a fundamental dashboard example for monitoring text generation inference deployed on Kubernetes, leveraging Knative-Serving.
Adapted from an official example, we added namespace and service variables.
To begin, you need to apply a service monitor to channel the metrics into Prometheus.
Data source config
Collector type:
Collector plugins:
Collector config:
Revisions
Upload an updated version of an exported dashboard.json file from Grafana
| Revision | Description | Created | |
|---|---|---|---|
| Download |