Deploying models on real-time endpoints

SageMaker endpoints serve real-time predictions using models hosted on fully managed infrastructure. They can be created and managed with either the SageMaker software development kit (SDK) or with an AWS SDK such as boto3.

You can find information on your endpoints in SageMaker Studio, under SageMaker resources/Endpoints.

Now, let's look at the SageMaker SDK in greater detail.

Managing endpoints with the SageMaker SDK

The SageMaker SDK lets you work with endpoints in several ways, as outlined here:

• Configuring an estimator, training it with fit(), deploying an endpoint with deploy(), and invoking it with predict()
• Importing and deploying a model
• Invoking an existing endpoint
• Updating an existing endpoint

We've used the first scenario in many examples so far. Let's look at the other ones.

Importing and deploying an XGBoost model

This is useful when you want to import a model that wasn...