AWS Certification Exam AI Practitioner (Practice Questions) set13
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 26 / 65
I want to efficiently host many small models on a single endpoint, loading models on demand for inference as requests come in. Which deployment approach is optimal?
①Amazon SageMaker Serverless Inference
②Amazon SageMaker Real-Time Endpoint
③AWS Lambda
④Amazon Elastic Inference
⑤Amazon SageMaker Multi-Model Endpoint