Semi Doped cover image

ARM AGI CPU has entered the chat, TurboQuant thrashes memory stocks

Semi Doped

00:00

Why KV cache matters and HBM role

Vikram and Austin outline key-value cache usage in inference and why fast memory like HBM is important.

Play episode from 09:56
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