Ram Janovski

DCGM exporter is not picking the pods that are using vGPU, making it hard to to track utilization of the pods. is there any workaround to monitor GPU utilization with...

### What happened? followed the instructions of adding prometheus metrics: litellm_settings: success_callback: [ "prometheus" ] failure_callback: [ "prometheus" ] service_callback: ["prometheus_system"] and /metrics just reports `307 Temporary Redirect` ### Relevant...