At this point, we have built our models in AWS and would like to ship them to production. We know that there is a variety of different contexts in which models should be deployed. In some cases, it's as easy as generating a CSV of actions that would be fed to some system. Often, we just need to deploy a web service capable of making predictions. However, there are special circumstances in which we need to deploy these models to complex, low-latency, or edge systems. In this chapter, we will look at the different ways to deploy machine learning (ML) models to production.
In this chapter, we will cover the following topics:
- SageMaker model deployment
- Apache Spark model deployment
