@article{siriuscontextualsparsitywithcorrection, title = {Sirius: Contextual Sparsity with Correction for Efficient LLMs}, author = {Yang Zhou and Zhuoming Chen and Zhaozhuo Xu and Victoria Lin and Beidi Chen}, year = {2024}, eprint = {2409.03856}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.03856v1}, }