KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization

Mingbo Song, Heming Xia, Jun Zhang, Chak Tou Leong, Qiancheng Xu, Wenjie Li, Sujian Li

Published: 2026, Last Modified: 11 Apr 2026EACL (Findings) 2026EveryoneRevisionsBibTeXCC BY-SA 4.0
Loading