Yankun, Hong

1. SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention
   2025/02/21 by Yankun, Hong, Xing, Li, Hui-Ling, Zhen +3 · 2 citations
   #68T50 #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)