NVIDIA AI Podcast cover image

Powering the AI Inference Wave with EPRI's Ben Sooter - Ep. 292

NVIDIA AI Podcast

00:00

Training vs. inference energy demand

Ben distinguishes model training from inference, noting inference consumes around 80% of a model's lifetime compute.

Play episode from 04:03
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