A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression Alessio Devoto author Yu Zhao author Simone Scardapane author Pasquale Minervini author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication devoto-etal-2024-simple 10.18653/v1/2024.emnlp-main.1027 https://aclanthology.org/2024.emnlp-main.1027/ 2024-11 18476 18499