Mixture of Attentions For Speculative Decoding

4 October 2024

Matthieu Zimmer

Haitham Bou Ammar

Jun Wang

Papers citing "Mixture of Attentions For Speculative Decoding"

2 / 2 papers shown

Title
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding J. Li Yixing Xu Haiduo Huang Xuanwu Yin D. Li Edith C. -H. Ngai E. Barsoum 42 0 0 13 Mar 2025
Speculative Decoding and Beyond: An In-Depth Survey of Techniques Y. Hu Zining Liu Zhenyuan Dong Tianfan Peng Bradley McDanel S. Zhang 82 0 0 27 Feb 2025