MLA-C01 Question 256
Single answerYou are a Machine Learning Engineer tasked with deploying a trained ML model to production for real-time inference. The model needs to handle high traffic with minimal latency. Which AWS service and feature combination would best meet these requirements?
- A
Deploy the model using Amazon SageMaker Hosting Services with an endpoint configured for auto-scaling.
- B
Deploy the model using Amazon SageMaker Batch Transform for periodic batch inference jobs.
- C
Deploy the model as a Docker container on Amazon Elastic Kubernetes Service (EKS) with a custom scaling mechanism.
- D
Deploy the model using Amazon SageMaker Neo to optimize the model for edge devices with low latency.
Show answer and explanation
Correct answer: A
Explanation
Amazon SageMaker Hosting Services is specifically designed for deploying ML models to serve real-time predictions with low latency. It supports features like auto-scaling, which makes it ideal for handling high traffic scenarios efficiently. Other options, such as Batch Transform, are not suitable for real-time inference, and EKS requires more manual setup compared to SageMaker Hosting Services.
- A. Correct.
This is the correct answer. Amazon SageMaker Hosting Services allows you to deploy models as real-time endpoints and supports auto-scaling to handle varying traffic while maintaining low latency.
- B. Incorrect.
This is incorrect. Amazon SageMaker Batch Transform is designed for batch inference, not real-time inference, and is not suitable for applications that require low latency.
- C. Incorrect.
This is not the best option. While EKS provides flexibility for deployment, it requires significant custom setup for scaling and managing low latency, which is handled more efficiently by SageMaker Hosting Services.
- D. Incorrect.
This is incorrect. Amazon SageMaker Neo optimizes models for edge devices, but it does not provide real-time endpoint capabilities for handling high traffic with minimal latency.