The Rundown: Daily AI & Compute

DiffusionGemma breaks the token-by-token bottleneck: open 26B MoE decodes 4x faster, served day-0 on SGLang

An episode of The Rundown: Daily AI & Compute. Follow topics, places and searches across every show — on podcasts.so, a podcast player that indexes what episodes actually talk about.

Download on the App Store

Already have it? Open in the app