To reduce GPU usage charges over weekends, an administrator decides to temporarily pause all active endpoints.
Which action in Nutanix Enterprise AI supports this goal?

• A. Scale inference pods to zero
• B. Hibernate the endpoints
• C. Detach the LLMs from endpoints
• D. Apply a read-only license

An administrator notices increased model inference latency and frequent timeout errors in a Nutanix AI deployment during peak usage.
What is the most effective action to troubleshoot and resolve the performance issue?

• A. Disable logging and monitoring tools to free up system resources.
• B. Reduce the number of API keys to limit external access to the model.
• C. Restart the Nutanix Kubernetes cluster to clear cached memory and reset service states.
• D. Analyze resource metrics and scale out the model service to handle increased loaD.

An AI/ML admin is testing access to an endpoint using Open AI compatible clients, but is unable to successfully access the endpoint.
What could be the issue?

• A. Endpoint has not been configured with the right LLM.
• B. Endpoint as been created by another AI/ML admin.
• C. API key has been removed from the endpoint.
• D. API key has been created by another AI/ML admin.

Which task is an AI/ML User unable to perform in Nutanix Enterprise AI?

• A. View a LLM that was imported by a different user.
• B. Delete an endpoint that they previously createD.
• C. Create an API key to access an AI inference endpoint.
• D. Test an AI inference endpoint that they previously createD.

Which widget within the Endpoint Details page can an administrator verify the memory usage associated with the endpoint?

• A. Infrastructure Summary
• B. Number of Compute Instances
• C. API Requests Trends
• D. Endpoints (Top 5)