Latent MoE

topic on 1 show · 1 statements across 1 episodes

the MAD Podcast

1 statements about Latent MoE, every show

MAD Assertion Supported
Catanzaro: Nemotron 3's Latent MoE quadruples experts for same inference cost
“Latent MOE is a specific innovation that we have in NemoTron three family. And what it does is actually reduces the amount of communication that has to be sent through NVLink during MOE computations by basically down projecting it. So, you know, every token pr…”
Bryan Catanzaro Jul 2, 2026 ▶ 46:00 Inside Nemotron & NVIDIA’s AI Lab | Bryan Catanzaro

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.