H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
作者:作者信息待提取 · 单位:University of Texas at Austin, 2Stanford University, 3University of California, San Diego, University of California, Berkeley, 5Adobe Research, 6Meta AI (FAIR), 7Carnegie Mellon University · 来源:NeurIPS · 发布日期:2023/06