Gradient Dissent: Conversations on AI cover image

Cristóbal Valenzuela — The Next Generation of Content Creation and AI

Gradient Dissent: Conversations on AI

00:00

Scaling Up Your Models?

We mostly use by torch for or full models We have a cluster Basically native us cluster that scales based on compute and demand. There are some, uh, web gl kind of like acceleration stuff we're doing to make things really smooth. And then the inference pipeline where we're writing everything like C++ to make it like super super efficient and like fast specifically since you're decoding and coding videos on real time.

Transcript
Play full episode

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