AWS AI Practitioner
A company needs to evaluate foundation models (FMs) for a real-time customer service application. The application requires fast responses to customer queries. Which FM characteristic should the company prioritize?
A
Training data size
B
Inference latency
✓ Correcta
C
Number of parameters
D
Fine-tuning capability
Explicación
Inference latency measures the speed at which an FM processes requests and delivers outputs. For a real-time customer service application that requires fast responses, inference latency is the most critical characteristic to prioritize when selecting a foundation model.