-
Notifications
You must be signed in to change notification settings - Fork 71
Open
Description
After this pr, models are lazily initialized when the first prediction occurs. That leads to the cached artifacts being retrieved for every prediction, which adds latency. Also, this means that the latency for downloading models is added in the first prediction, rather than the module initialization, which could be done at building time.
We should more extensively test to assess how much latency it adds, and think of ways to trigger the initialization outside of an actual request.
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels