MLA-C01 Question 312
Single answerYou are a Machine Learning Engineer tasked with deploying a machine learning model as a REST API. The model should be containerized, and the deployment must easily scale based on incoming traffic. Additionally, the solution should minimize infrastructure management overhead while integrating seamlessly with AWS services. Which AWS service should you use for deploying your containerized model?
- A
Amazon ECS with AWS Fargate
- B
Amazon S3
- C
AWS Lambda
- D
Amazon SageMaker
Show answer and explanation
Correct answer: A
Explanation
Amazon ECS with AWS Fargate is the best choice for deploying a containerized machine learning model as a REST API because it provides seamless scaling and eliminates the need to manage the underlying infrastructure. Fargate works well with containerized workloads and integrates smoothly with other AWS services, making it ideal for this use case.
- A. Correct.
Amazon ECS with AWS Fargate is a container orchestration service that works well with containerized applications. Fargate eliminates the need to manage the underlying infrastructure, allowing you to focus on deploying and scaling the model based on traffic.
- B. Incorrect.
Amazon S3 is a storage service and cannot directly run or scale containerized applications. It is not suitable for deploying a machine learning model as a REST API.
- C. Incorrect.
AWS Lambda is a serverless compute service, but it is not specifically designed for running containerized applications. While Lambda supports container images, it has size and execution time limitations that may not suit machine learning workloads requiring scalable containers.
- D. Incorrect.
Amazon SageMaker is a machine learning service that supports model training and hosting. While it can deploy models, it is not a general-purpose container orchestration service and may not provide the desired flexibility for REST API scaling in this scenario.