A hatchery lab uploads one long raw-instrument file per sample. Scoring plus preprocessing overshoots the real-time timeout, and the file is too large for a serverless payload, but a same-morning queued result is fine. Which mode fits?

Short Explanation

One long instrument file overshoots the real-time timeout and is too big for serverless. Async inference fits. GPU versus CPU picks a host, not the serving mode.

Full Explanation

Asynchronous inference is the distinction when payload size and processing time exceed real-time and serverless limits. GPU versus CPU is host selection, not that serving-mode choice.

×