KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches Jiayi Yuan author Hongyi Liu author Shaochen Zhong author Yu-Neng Chuang author Songchen Li author Guanchu Wang author Duy Le author Hongye Jin author Vipin Chaudhary author Zhaozhuo Xu author Zirui Liu author Xia Hu author 2024-11 text Findings of the Association for Computational Linguistics: EMNLP 2024 Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication yuan-etal-2024-kv 10.18653/v1/2024.findings-emnlp.266 https://aclanthology.org/2024.findings-emnlp.266/ 2024-11 4623 4648