AWS Certification Exam AI Practitioner (Practice Questions) set14
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 18 / 65
Which AWS options are effective for running large transformer models for inference at low cost?
①Scale out using only general-purpose CPU instances.
②Offload inference to client devices.
③Use a workflow that loads the full model every time.
④Use inference accelerators such as AWS Inferentia and Graviton.
⑤Scale the model size arbitrarily large and run it on a single instance.