Google releases Multi-Token Prediction drafters for its Gemma 4 models, which use a form of speculative decoding to guess future tokens for faster inference (Ryan Whitwam/Ars Technica)

Ryan Whitwam / Ars Technica:
Google releases Multi-Token Prediction drafters for its Gemma 4 models, which use a form of speculative decoding to guess future tokens for faster inference  —  Google launched its Gemma 4 open models this spring, promising a new level of power and performance for local AI.

from Techmeme https://ift.tt/nGliUF8