← Volver

Vista previa

Editar
AWS AI Practitioner

A company has developed a large language model (LLM) and wants to make the LLM available to multiple internal teams. Which inference mode should be used for a chatbot that needs to process real-time user queries with minimal latency?

A Batch transform
B Real-time inference ✓ Correcta
C Asynchronous inference
D Serverless inference