@article{asymkvenabling1bitquantizationofkv, title = {AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations}, author = {Qian Tao and Wenyuan Yu and Jingren Zhou}, year = {2024}, eprint = {2410.13212}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13212v1}, }