Question
A company uses Amazon SageMaker for its ML pipeline in a production environment. The company has large input data sizes up to 1 GB and processing times up to 1 hour. The company needs near real-time latency.
Which SageMaker inference option meets these requirements?
- A. Real-time inference
- B. Serverless inference
- C. Asynchronous inference Correct
- D. Batch transform
Explanation
Asynchronous inference in Amazon SageMaker is suitable for scenarios where the input data sizes are large and processing times are long, while still requiring near real-time responses. This option allows the model to process requests without waiting for a response, which fits the company's need for handling up to 1 GB of input data with processing times up to 1 hour.
