Syllaro Academy

AWS Certified AI Practitioner

Types of Inferencing

Once a model is trained, inference is how it serves predictions. Compare real-time, batch, asynchronous, and serverless inference and match each to latency, payload, and traffic needs.

Beginner 15 minutes 4 Learning Objectives
  1. Define inference and distinguish it from training
  2. Compare real-time, batch, asynchronous, and serverless inference
  3. Match an inference type to latency, payload, and traffic requirements
  4. Map the inference types to Amazon SageMaker options