Latent Space: The AI Engineer Podcast cover image

A Technical History of Generative Media

Latent Space: The AI Engineer Podcast

00:00

Navigating the Challenges of Serverless GPU Scaling

This chapter explores the complexities of serverless GPU technology, focusing on the hurdles of scaling and orchestration. It highlights the authors' journey in optimizing performance and cost through innovative solutions and custom kernel development across various cloud platforms.

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