QoKV: Comprehending and Surpassing the Hurdles of KV Cache Quantization.
Jinguang Wang, Yuexi Yin, Haifeng Sun, Tingting Yang, Qi Qi, Zirui Zhuang, Jingyu Wang
Browse the full ICASSP paper archive.
Jinguang Wang, Yuexi Yin, Haifeng Sun, Tingting Yang, Qi Qi, Zirui Zhuang, Jingyu Wang
Browse the full ICASSP paper archive.