AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations

AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations Qian Tao author Wenyuan Yu author Jingren Zhou author 2025-01 text Proceedings of the 31st International Conference on Computational Linguistics Owen Rambow editor Leo Wanner editor Marianna Apidianaki editor Hend Al-Khalifa editor Barbara Di Eugenio editor Steven Schockaert editor Association for Computational Linguistics Abu Dhabi, UAE conference publication tao-etal-2025-asymkv https://aclanthology.org/2025.coling-main.158/ 2025-01 2316 2328