AI + a16z cover image

Dylan Patel on the AI Chip Race - NVIDIA, Intel & the US Government

AI + a16z

00:00

Specialized Chips: Prefill vs Decode Architectures

Discussion of disaggregating pre-fill and decode workloads and how CPX and Rubin cards optimize those workloads.

Play episode from 01:28:21
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