A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

18 October 2024

Papers citing "A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference"

2 / 2 papers shown

Title
Prefill-Based Jailbreak: A Novel Approach of Bypassing LLM Safety Boundary Yakai Li Jiekang Hu Weiduan Sang Luping Ma Jing Xie Weijuan Zhang Aimin Yu Shijie Zhao Qingjia Huang Qihang Zhou AAML 40 0 0 28 Apr 2025
Tensor Product Attention Is All You Need Yifan Zhang Yifeng Liu Huizhuo Yuan Zhen Qin Yang Yuan Q. Gu Andrew Chi-Chih Yao 60 8 0 11 Jan 2025