Skip to content

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding.

Yike Zhang, Zhiyuan He, Huiqiang Jiang, Chengruidong Zhang, Yuqing Yang, Jianyong Wang, Lili Qiu

VenueA*EMNLP
Year2025
ProceedingsEMNLP

Browse the full EMNLP paper archive.