Inference scaling

4 posts · 3 sources

DecagonBlog20 Aug

Scaling real-time text-to-speech inference

MetaBlog31 Mar

Meta Adaptive Ranking Model: Bending the Inference Scaling Curve to Serve LLM-Scale Models for Ads

ModalBlog25 Mar

How Doppel eliminated ML infrastructure tax with Modal

DecagonBlog

Introducing Chord: a speech model built for customer conversations