Frozen Multi‑Token Prediction Slashes Gemini Nano Latency on Pixel Phones
Google Research unveiled frozen Multi-Token Prediction (MTP), a retrofit that speeds up Gemini Nano on Pixel phones without fine‑tuning separate draft models. By integrating a lightweight transformer into the frozen model, MTP cuts inference latency and power use, making on‑device AI features like notification summaries and proofreading snappier and more battery‑friendly.