Re:Wootric moved ML deployment pipeline from AWS to GCP
by rsmith49 on Tuesday April 14, 2020 @02:21PM
(#22869517)
Making the calls to the corresponding model from Flask was actually easier on AWS, since they were loaded into memory. Unfortunately, the scaling issues/excessive load times were big enough of an issue that we had to make the switch, as our number of hosted models continues to grow.
[ Parent
| on HN ]
There are no comments on this comment yet.