PapersBuilders13:10Chinese contentLoopVQ:面向 Looped Transformer 的亚 1-bit KV Cache 量化方法.looped 模型参数省但 KV cache 爆炸,这篇提出 0.5bit 量化方案,SGLang 实测吞吐最高涨 6.1 倍,做部署的可以看看。#LoopVQ#KV Cache#量化#Looped TransformeraarXiv cs.LG@Minsoo Cheong, Sungjoo YooSourceRead laterReadWorth followingUsefulFollow LoopVQ