試験
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 32 / 65
Which AWS configuration is appropriate for providing machine learning inference with high throughput and low latency?
①Scale low-spec general-purpose instances within a single Availability Zone.
②Deploy GPU-equipped, inference-optimized instances across multiple Availability Zones and autoscale them.
③Run inference on fully serverless static hosting.
④Use only old on-premises GPU servers.
⑤Execute inference logic directly in the database using SQL.