Exam DP-100 All QuestionsBrowse all questions from this exam
Question 98

HOTSPOT -

You are using an Azure Machine Learning workspace. You set up an environment for model testing and an environment for production.

The compute target for testing must minimize cost and deployment efforts. The compute target for production must provide fast response time, autoscaling of the deployed service, and support real-time inferencing.

You need to configure compute targets for model testing and production.

Which compute targets should you use? To answer, select the appropriate options in the answer area.

NOTE: Each correct selection is worth one point.

Hot Area:

    Correct Answer:

    Box 1: Local web service -

    The Local web service compute target is used for testing/debugging. Use it for limited testing and troubleshooting. Hardware acceleration depends on use of libraries in the local system.

    Box 2: Azure Kubernetes Service (AKS)

    Azure Kubernetes Service (AKS) is used for Real-time inference.

    Recommended for production workloads.

    Use it for high-scale production deployments. Provides fast response time and autoscaling of the deployed service

    Reference:

    https://docs.microsoft.com/en-us/azure/machine-learning/concept-compute-target

Discussion
michaelmorar

"You need to configure compute targets for model testing and production." Suggests that we don't need a target for training and evaluation, ONLY to test the deployed model. Therefore: 'Local Web Service' for Test, and AKS for PROD.

ahson0124

On exam 2023-02-15

Yuriy_Ch

Exactly this question was on exam 07/March/2023

FlexingD

ACI for testing + 1

daviskv74

Chat GPT says for testing, ACI suitable

prabhjot

i agress ACI for testing and for Production AKS

claps92

ACI for testing (minimizes the deployment effort)

PremPatrick

LocalWebservice for testing (not sure though!) https://learn.microsoft.com/en-us/azure/machine-learning/concept-compute-target

klowqw

ACI for testing

klowqw

Local for testing

sanctafrax

Question states it is for model testing. Therefore ACI is not needed, Local Webservice should be fine. AKS is required for prod

Edriv

https://www.techtarget.com/searchcloudcomputing/definition/Azure-Container-Instances#:~:text=Azure%20Container%20Instances%20is%20a%20service%20that%20enables,having%20to%20provision%20or%20manage%20any%20underlying%20infrastructure.

reddragondms

Local web services and azure container instances are listed under compute targets for inference, not training targets. Wouldn't the order for "minimize cost and deployment efforts" for testing be first "Local computer" then "Azure ML compute cluster"? https://learn.microsoft.com/en-us/azure/machine-learning/concept-compute-target