BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Open Webpage

Peng Xu, Wenqi Shao, Mengzhao Chen, Shitao Tang, Kaipeng Zhang, Peng Gao, Fengwei An, Yu Qiao, Ping Luo

Published: 2024, Last Modified: 02 Mar 2025ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0