AI-900: Deploying Real-Time Inference Pipelines: Azure Machine Learning Options

Learn about the various deployment options available in Azure Machine Learning for deploying real-time inference pipelines as a service. Explore deploying models to a local web service, Azure Container Instances, Azure Kubernetes Service (AKS), or Azure Machine Learning compute. Discover the best approach for serving your machine learning models efficiently and reliably.

Question

From Azure Machine Learning designer, to deploy real time inference pipeline as a service for others to consumer, you must deploy the model to __________.

A. a local web service.
B. Azure Container Instances.
C. Azure Kubernetes Service (AKS).
D. Azure Machine Learning compute.

Answer

C. Azure kubernetes services (AKS)

Explanation

The correct answer is C. Azure Kubernetes Service (AKS).

Azure Kubernetes Service (AKS) is a managed Kubernetes service that allows you to deploy and manage containerized applications in the cloud. You can use AKS to host your real-time inference pipelines as web services that can scale to meet your demand. AKS provides high availability, load balancing, security, and monitoring for your web services.

Azure Machine Learning designer is a drag-and-drop UI interface for building machine learning pipelines in Azure Machine Learning. You can use designer to create, test, and deploy real-time inference pipelines as web services. To deploy a real-time inference pipeline as a web service, you need to specify a compute target where the web service will run. The compute target can be either Azure Container Instances (ACI) or Azure Kubernetes Service (AKS).

Azure Container Instances (ACI) is a service that allows you to run containers on-demand in a serverless Azure environment. ACI is suitable for testing and development scenarios, or for lightweight web services that do not require advanced features or scalability. ACI provides fast and simple deployment, but it has some limitations, such as lower performance, less control, and higher costs compared to AKS.

Azure Machine Learning compute is a managed compute resource that you can use to train your machine learning models or run your batch inference pipelines. Azure Machine Learning compute is not a valid compute target for deploying real-time inference pipelines as web services.

A local web service is a web service that runs on your local machine or a cloud-based virtual machine. A local web service is not a valid compute target for deploying real-time inference pipelines as web services from Azure Machine Learning designer. You can use a local web service for testing and debugging purposes, but you need to use Azure Machine Learning SDK to create and deploy a local web service.

To perform real-time inferencing, you must deploy a pipeline as a real-time endpoint. Real-time endpoints must be deployed to an Azure Kubernetes Service cluster.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.