MLA-C01 Question 328
Single answerYou are a Machine Learning Engineer tasked with deploying a model to production on AWS. The model needs to handle high throughput requests in near real-time and must automatically scale based on incoming traffic. Which AWS service would be the most appropriate to host your model?
- A
Amazon SageMaker Hosting Services
- B
AWS Lambda
- C
Amazon EC2
- D
Amazon EMR
Show answer and explanation
Correct answer: A
Explanation
Amazon SageMaker Hosting Services is purpose-built for deploying machine learning models in production. It provides features such as real-time inference endpoints, automatic scaling, and model versioning, which meet the requirements of high throughput and near real-time request handling in this scenario. Other services, such as AWS Lambda, EC2, and EMR, do not offer the same level of integration and optimization for machine learning-specific workloads.
- A. Correct.
Amazon SageMaker Hosting Services is designed specifically for deploying machine learning models with capabilities such as automatic scaling, real-time inference, and endpoint management, making it an ideal choice for this scenario.
- B. Incorrect.
AWS Lambda is a serverless compute service that can run your code in response to events, but it is not optimized for hosting machine learning models requiring high throughput or real-time scaling.
- C. Incorrect.
Amazon EC2 offers flexible compute capacity but lacks built-in features for deploying, managing, and scaling machine learning models specifically.
- D. Incorrect.
Amazon EMR is a big data processing service used for distributed data processing frameworks like Hadoop and Spark, not for deploying machine learning models for real-time inference.