You use Azure Machine Learning designer to create a real-time service endpoint. You have a single Azure Machine Learning service compute resource. You train the model and prepare the real-time…

The correct answer is B. Azure Kubernetes Services. For publishing a real-time inference pipeline as a web service in Azure Machine Learning, Azure Kubernetes Service (AKS) is the correct compute type. AKS is the recommended production-grade compute target for real-time scoring endpoints because it provides scalability, high…

Train and deploy models

Question

You use Azure Machine Learning designer to create a real-time service endpoint. You have a single Azure Machine Learning service compute resource. You train the model and prepare the real-time pipeline for deployment. You need to publish the inference pipeline as a web service. Which compute type should you use?

Options

Aa new Machine Learning Compute resource
BAzure Kubernetes Services
CHDInsight
Dthe existing Machine Learning Compute resource
EAzure Databricks

How the community answered

(22 responses)

A
5% (1)
B
82% (18)
C
5% (1)
E
9% (2)

Explanation

For publishing a real-time inference pipeline as a web service in Azure Machine Learning, Azure Kubernetes Service (AKS) is the correct compute type. AKS is the recommended production-grade compute target for real-time scoring endpoints because it provides scalability, high availability, and low-latency responses suitable for web service deployments. Azure Machine Learning Compute (options A and D) is designed for training jobs, not real-time inference hosting. HDInsight (C) is a big data processing service not used for ML inference. Azure Databricks (E) is a Spark-based analytics platform, also not used for hosting real-time ML endpoints.

Topics

#Azure ML deployment#Real-time endpoints#AKS#Compute targets

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice