MILLION: MasterIng Long-Context LLM Inference Via Outlier-Immunized KV Product QuaNtization

Zongwu Wang, Haibing Guan(Shanghai Jiao Tong University), Peng Xu(Chinese Academy of Tropical Agricultural Sciences), Qingxiao Sun, Gezi Li(Ministry of Ecology and Environment), Xuan Wang(Affiliated Hospital of Southwest Medical University), Yiwei Hu, Cheng Li(Huawei Technologies (China)), Li Jiang, Fangxin Liu(Shanghai Jiao Tong University)
Unknown
June 22, 2025
Cited by 0


Related Papers