The New Stack Podcast cover image

Do All Your AI Workloads Actually Require Expensive GPUs?

The New Stack Podcast

00:00

When CPUs beat GPUs for inference

Andrei argues many inference tasks, embeddings and smaller LLMs can run more cost-effectively on Axion CPUs than GPUs.

Play episode from 19:15
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