MLA-C01 · Question #147
An ML engineer needs to deploy a trained model that is based on a genetic algorithm. The algorithm solves a complex problem and can take several minutes to generate predictions. When the model is…
The correct answer is C. Deploy the model to an Amazon SageMaker Asynchronous Inference endpoint. SageMaker Asynchronous Inference is designed for models with long processing times and large payloads. It can handle input data up to 1 GB and avoids holding open connections during long inference runs, reducing operational overhead compared to managing EC2 or ECS…
Question
An ML engineer needs to deploy a trained model that is based on a genetic algorithm. The algorithm solves a complex problem and can take several minutes to generate predictions. When the model is deployed, the model needs to access large amounts of data to process requests. The requests can involve as much as 100 MB of data. Which deployment solution will meet these requirements with the LEAST operational overhead?
Options
- ADeploy the model to Amazon EC2 instances in an Auto Scaling group behind an Application Load
- BDeploy the model to an Amazon SageMaker real-time endpoint.
- CDeploy the model to an Amazon SageMaker Asynchronous Inference endpoint.
- DPackage the model as a container. Deploy the model to Amazon Elastic Container Service
How the community answered
(36 responses)- A19% (7)
- B3% (1)
- C67% (24)
- D11% (4)
Explanation
SageMaker Asynchronous Inference is designed for models with long processing times and large payloads. It can handle input data up to 1 GB and avoids holding open connections during long inference runs, reducing operational overhead compared to managing EC2 or ECS infrastructure. This makes it the best fit for the genetic algorithm model that takes minutes and processes large
Topics
Community Discussion
No community discussion yet for this question.