Answer-first summary for fast verification
Answer: Azure Kubernetes Services
The correct answer is B (Azure Kubernetes Services) because the question specifically asks about publishing an inference pipeline as a web service for real-time endpoint deployment. According to Azure Machine Learning best practices and the community consensus (with B receiving 100% community support and multiple comments confirming AKS is used for real-time inference), AKS is the appropriate compute target for deploying real-time web services. While option D (the existing Machine Learning Compute resource) might seem cost-effective, it's primarily used for training and batch inference, not real-time web service deployment. The Microsoft documentation referenced in the discussion confirms that only AKS can be used for real-time inference deployment scenarios.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are using Azure Machine Learning designer to create a real-time endpoint. You have a single Azure Machine Learning compute instance. After training the model and preparing the real-time pipeline for deployment, you need to publish the inference pipeline as a web service. Which compute type should you select?
A
a new Machine Learning Compute resource
B
Azure Kubernetes Services
C
HDInsight
D
the existing Machine Learning Compute resource
E
Azure Databricks
No comments yet.