Hi Render Team,
I am running a web app that uses an ML model locally on my MacBook with an M2 Pro chip (12 cores, 16 GB memory) with ease. The model takes a maximum of 1-2 seconds to run locally. However, when I deployed the same app on Render, it hits 100% CPU usage and runs indefinitely without producing any results.
I have tried all your premium web service options, including the one with 8 CPUs, but none have resolved the issue. Any advice you could provide would be greatly appreciated.
Thank you.