Medusa

Concept

An older technique for speculative decoding, mentioned as a historical example in the book 'Inference Engineering'.

Mentioned in 1 video

Videos Mentioning Medusa

The Inference Frontier: 10x Faster Models to Self-Optimizing AI — Philip Kiely & Ali Taha, Baseten

The Inference Frontier: 10x Faster Models to Self-Optimizing AI — Philip Kiely & Ali Taha, Baseten

Latent Space

An older technique for speculative decoding, mentioned as a historical example in the book 'Inference Engineering'.