Serving ML Models Using a Fully Managed Cloud Solution
We have, so far, looked at some tools such as TensorFlow Serving, Ray Serve, and BentoML. In this chapter, we will see how we can serve an ML model using a fully managed cloud solution. There are a few popular cloud solutions provided by Amazon, Google, Microsoft, IBM, and more. In this chapter, we will discuss how we can serve an ML model using Amazon SageMaker. Explaining all aspects of Amazon SageMaker (https://aws.amazon.com/sagemaker/) is beyond the scope of this book. We will only introduce some basic concepts, deploy a model, and test whether we can invoke the model.
At a high level, we are going to cover the following main topics in this chapter:
- Introducing Amazon SageMaker
- Using Amazon SageMaker to serve a model
