Types of inference · Question 9 of 12
A service must analyse large video files, a single request takes up to 30 minutes, and requests arrive irregularly. Which Amazon SageMaker AI inference option fits best?
1 answer is correct. Medium
Show answer
Answer
- A Asynchronous inference
Explanation
Asynchronous inference queues requests, processes them in the background and stores the result in Amazon S3. It is designed for large payloads up to 1 GB and processing times of up to one hour, and it can scale down to zero instances when idle. Real-time and serverless endpoints are built for short requests with an immediate response.