Big Cyber Monday Sale Discount Flat 70% Offer - Ends in 0d 00h 00m 00s - Coupon code: 70diswrap

Nutanix NCP-AI Dumps

Page: 1 / 8
Total 75 questions

Nutanix Certified Professional - Artificial Intelligence NCP-AI 6.10 Questions and Answers

Question 1

An AI/ML Admin initiates an import of a new Large Language Model (LLM) from Hugging Face using its Model URL into Nutanix Enterprise AI.10

After the import process begins, the LLM's status on the Models page changes to Pending.11

Based on this status, what is the most probable cause for the delay?

Options:

A.

The LLM is a custom model that Nutanix has not validated.12

B.

The NVIDIA GPU Operator is not installed on the Kubernetes cluster.

C.

The system is awaiting the necessary cluster resources.

D.

The Hugging Face access token provided is unauthorized.

Question 2

A junior developer has been granted access to an endpoint but is unsure how to send requests to it.

Which feature in the endpoint details page will help them get started with integration?

Options:

A.

User Role Editor

B.

View API Logs

C.

Endpoint Name

D.

Sample Request code

Question 3

An administrator has been asked to troubleshoot the import of a new NIM LLM in NAI. The import Status is Pending.

What could be the most common issue?

Options:

A.

LLM repository read access restriction.

B.

Unauthorized Hugging Face token.

C.

Required storage space is not available.

D.

System is downloading the LLM.

Question 4

An administrator is setting up Nutanix Enterprise AI with a custom domain (ai.company.com) and must comply with security policies requiring a valid TLS certificate from the corporate certificate authority (CA).

Which two steps are necessary to complete this configuration successfully? (Choose two.)

Options:

A.

Add a DNS A record pointing ai.company.com to the NAI IP address in a DNS server.

B.

Create a DNS PTR record for ai.company.com to match the DNS A record.

C.

A CA signed TLS certificate for the configured NAI FQDN.

D.

Use the Nutanix Prism interface to directly assign the FQDN ai.company.com to the NAI IP address.

Question 5

Which user type is the first AI/ML admin user who installs Nutanix Enterprise AI on the Kubernetes cluster?

Options:

A.

Super User

B.

AI/ML User

C.

AI/ML Admin

D.

Super Admin

Question 6

Which Nutanix AI deployment platform is supported?

Options:

A.

Native Kubernetes

B.

AWS EC2

C.

Nutanix NKE

D.

On-premises NCI

Question 7

What is the minimum number of supported GPUs required to deploy Google pre-validated LLMs?

Options:

A.

1

B.

2

C.

3

D.

4

Question 8

An administrator logs onto the Nutanix Enterprise AI Dashboard and notices that all current GPU and non-GPU Endpoints are marked as Hibernated. After reviewing the Audit Events section, the administrator notes that no anomalous behavior events have occurred since the day before.

What is the most likely cause as to why all of the current Endpoints are hibernated seemingly at random?

Options:

A.

The GPU GB license has been exceeded.

B.

The vCPU and GPU GB licenses has expired.

C.

The vCPU and GPU GB trial licenses are close to expiry.

D.

The vCPU license has expired.

Question 9

During NAI installation, a Docker Account is required.

Where should an administrator generate the access token?

Question 10

What prerequisites must be skipped when adding GPU nodes to a managed Kubernetes service on an Azure AKS cluster using Azure CLI?

Options:

A.

Install the GPU driver

B.

Install the Worker driver

C.

Install the Worker Connector

D.

Install the GPU Connector

Question 11

An administrator needs to spot the busiest credentials at a glance.

Which Dashboard widget provides insight into the most frequently used credentials?

Options:

A.

Endpoints Summary

B.

API Keys (Top 5)

C.

Infrastructure Summary

D.

API Requests Trends

Question 12

Which deployment type of Nutanix Enterprise AI is supported in Amazon EKS?

Options:

A.

Standalone

B.

Cloud Cluster

C.

GPT-in-a-Box 2.0

D.

Bare Metal

Question 13

An administrator is troubleshooting a slow response from an inference endpoint used by multiple separate applications. The administrator has observed a huge increase in requests.

In order to identify which application is generating the huge increase in requests, what could the administrator do?

Options:

A.

Deactivate API keys one at a time.

B.

Increase the assigned compute resources.

C.

Reduce the assigned compute resources.

D.

Deactivate the inference endpoint.

Question 14

An administrator has been asked to verify why the URL NAI dashboard is inaccessible.

Which service could be impacted?

Options:

A.

istio

B.

metallb

C.

prometheus

D.

kserve

Question 15

An AI/ML administrator has been contacted by an endpoint owner who advises that one of their endpoints is not working properly anymore suggesting the API key has been removed. The AI/ML administrator can see that the API key is no longer listed under the endpoint.

What filter under the Audit Events page can the AI/ML administrator use to help understand what has happened?

Options:

A.

Action = Log Out; Entity Type = API Key

B.

Action = Delete; Entity Type = API Key

C.

Action = Log Out; Entity Type = Endpoint

D.

Action = Delete; Entity Type = Endpoint

Question 16

Corporate policy says that API keys should be deactivated, not deleted, when a compromise is suspected, but may need to be restored.

Which new status will the key display after the one-click Deactivate action?

Options:

A.

Pending

B.

Inactive

C.

Expired

D.

Failed

Question 17

Which GPU is currently supported for Nutanix AI deployment?

Options:

A.

V100

B.

T4

C.

L4

D.

A100

Question 18

An administrator has successfully completed the Create an Endpoint wizard and returned to the Endpoint widget to note that the new endpoint displays a status of Failed.

The administrator does not see any obvious error message associated with the failed status and decides to engage Nutanix Support.

Which command output should be provided when raising the Nutanix Support case?

Options:

A.

kubectl describe isvc endpoint_name -n nai-system

B.

kubectl describe isvc endpoint_name -n nai-admin

C.

kubectl exec isvc endpoint_name -n nai-admin

D.

kubectl exec isvc endpoint_name -n nai-system

Question 19

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?

Options:

A.

Reduce the number of API keys to limit external access to the model.

B.

Restart the Nutanix Kubernetes cluster to clear cached memory and reset service states.

C.

Disable logging and monitoring tools to free up system resources.

D.

Analyze resource metrics and scale out the model service to handle increased load.

Question 20

An administrator is configuring a container registry to store custom models for secure Nutanix Enterprise AI deployment. During testing, the administrator notices the registry is accessible both via HTTP and HTTPS, with a self-signed certificate.

Which two actions should the administrator take to meet the deployment prerequisites? (Choose two.)

Options:

A.

Disable HTTP on the container registry.

B.

Install Nutanix Enterprise AI in offline mode.

C.

Replace the certificate with a trusted TLS/SSL certificate.

D.

Ensure registry runs on the same node as the cluster.

Question 21

An administrator is configuring a new endpoint in Nutanix Enterprise AI (NAI) using an NVIDIA NIM model. During the configuration, the administrator notices that the Use GPU checkbox is selected and cannot be modified.

What is the reason the checkbox is locked in this state?

Options:

A.

Setting is locked due to a cluster-level policy restriction.

B.

All endpoints in NAI require using GPUs.

C.

System has already validated the endpoint configuration.

D.

These models require GPU resources to run.

Question 22

What minimum persistent storage is required for the nai-db app when deploying Nutanix Enterprise AI platform?

Options:

A.

2 GiB

B.

4 GiB

C.

2 TiB

D.

4 TiB

Page: 1 / 8
Total 75 questions