FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Yuxuan, Liang, Xiaozhuan, Wang, Xinghua, Ma, Jin, Liang, Haijin, Luo, Jinwen, Zuo, Xinyu, Duan, Lisheng, Yin, Yuyang, Chen, Xi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!