Pier cameras drop multi-hundred-megabyte clips that take many minutes to score. Clerks can wait for a queued result; they cannot block a synchronous HTTP call for an hour. Which serving mode fits?
Select an answer to reveal the explanation.
Short Explanation
Pier cameras drop huge clips that take many minutes. Async inference queues the payload and clerks wait for a result. Real-time wants a small sync call, batch is an offline file set, and Translate is not that mode.
Full Explanation
SageMaker asynchronous inference queues large payloads and long-running scores. Real-time expects a small synchronous call. Batch transform scores an offline file set with no per-request queue. Translate is not that mode.