MLOps.community  cover image

The Long Tail of ML Deployment // Tuhin Srivastava // #161

MLOps.community

00:00

How to Choose the Right Horizontal Scaling Setup for Height Traffic Partners

As you scale, board the things increase, which is the compute as well as the storage. You're talking about deploying things that are serving things that add in a way that'd be hard to serve in the past. And so whether that be, right now we're trying to deploy a, I think it's like a 60 billion parameter model with floating point 32, FP32 or something like that,. The largest use case is almost like a consumer use case right now, is at like a scale that we haven't thought about.

Play episode from 31:24
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app