Re:Wootric moved ML deployment pipeline from AWS to GCP
by LiamPa on Tuesday April 14, 2020 @02:54PM
(#22869953)
Why not just have a keep alive/warm style serverless function to prevent the start up latency?
[ Parent
| on HN ]
Re:Wootric moved ML deployment pipeline from AWS to GCP
by prabhatjha on Tuesday April 14, 2020 @03:04PM
(#22870089)
I am assuming you are talking about our deployment on GCP Cloud Run? We have thought about sending a heartbeat API call. It we notice any user experience friction because of this lag then we will definitely do that. As we said in the blog, this has not been a major pain point as of today.