BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models

Paper recorded by Signals 4 on 2026-10-20 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-20 on arXiv · recorded by Signals 4 on 2026-10-21

Category: cs.CL · 自然语言处理 · first seen 2026-10-21

Abstract

For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while multi-token prediction (MTP) methods reduce sequential decoding steps by predicting multiple future tokens in parallel. Although complementary, the direct combination of these methods cannot accelerate decoding at comparable qual

Read on arXiv →