CPP: Compensated Post-Training Pruning Approach for On-Device Large Language Model Services.
Junna Zhang, Yifei Hu, Chuntao Ding, Xiaoyan Zhao, Peiyan Yuan, Shangguang Wang
Browse the full ICWS paper archive.
Junna Zhang, Yifei Hu, Chuntao Ding, Xiaoyan Zhao, Peiyan Yuan, Shangguang Wang
Browse the full ICWS paper archive.