Exam AWS Certified Machine Learning - Specialty topic 1 question 230 discussion

Just additional information, Elastic Inference is being deprecated and recommendation is use AWS Inferentia

Option A can help you meet your requirements most cost-effectively because it enables you to choose the instance type that is best suited to the overall compute and memory needs of your application, and then separately specify the amount of inference acceleration that you need. This reduces inference costs by up to 75% because you no longer need to over-provision GPU compute for inference1.

We want to improve the inference of the model. That said, Letter B - C does not solve this problem. Letter D solves it, but at a very high cost. Letter A is correct, as we solve the problem at the lowest possible cost.

Use Amazon Elastic Inference on the SageMaker hosted endpoint would be the most cost-effective solution for increasing throughput and decreasing latency. Amazon Elastic Inference is a service that allows you to attach GPU-powered inference acceleration to Amazon SageMaker hosted endpoints and EC2 instances. By attaching an Elastic Inference accelerator to the SageMaker endpoint, you can achieve better performance with lower costs than using a larger, more expensive instance type.

"cost efficient" therefore A based on slide 20: https://pages.awscloud.com/rs/112-TZM-766/images/AL-ML%20for%20Startups%20-%20Select%20the%20Right%20ML%20Instance.pdf