MLOps.community  cover image

Serving LLMs in Production: Performance, Cost & Scale // CAST AI Roundtable

MLOps.community

00:00

Prefill vs decode: desegregated serving

Igor explains splitting requests into prefill and decode phases and optimizing each with specialized nodes.

Play episode from 39:52
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