@article{shadowllmpredictorbasedcontextualsparsit, title = {ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models}, author = {Yash Akhauri and Ahmed F AbouElhamayed and Jordan Dotzel and Zhiru Zhang and Alexander M Rush and Safeen Huda and Mohamed S Abdelfattah}, year = {2024}, eprint = {2406.16635}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.16635v2}, }