@article{ffsplitsplitfeedforwardnetworkfor, title = {FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference}, author = {Zirui Liu and Qingquan Song and Qiang Charles Xiao and Sathiya Keerthi Selvaraj and Rahul Mazumder and Aman Gupta and Xia Hu}, year = {2024}, eprint = {2401.04044}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.04044v1}, }