Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Siqi, Fang, Xuezhi, Xing, Xingrun, Han, Peng, Shang, Shuo, Wang, Yequan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!