@article{kiviatuningfreeasymmetric2bit, title = {KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache}, author = {Zirui Liu and Jiayi Yuan and Hongye Jin and Shaochen Zhong and Zhaozhuo Xu and Vladimir Braverman and Beidi Chen and Xia Hu}, year = {2024}, eprint = {2402.02750}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.02750v2}, }