Lex Fridman Podcast cover image

#381 – Chris Lattner: Future of Programming and AI

Lex Fridman Podcast

00:00

Abstraction of distributed deployment of large models

The modular compute platform dynamically partitions models with billions of parameters and distributes their execution across multiple machines, enabling unparalleled efficiency. So how do you do this abstraction of distributed deployment of large models? Yeah, so one of the really interesting tensions. There's a whole bunch of stuff that goes into that.

Play episode from 01:04:12
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