試験
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 21 / 65
I want to expose inference from a generative model as a low‑latency endpoint in production. Which AWS service lets you easily deploy and scale models in a fully managed way?
①AWS Lambda
②Amazon EC2
③Amazon SageMaker
④AWS Batch
⑤Amazon ECS