ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models Yash Akhauri author Ahmed F AbouElhamayed author Jordan Dotzel author Zhiru Zhang author Alexander M Rush author Safeen Huda author Mohamed S Abdelfattah author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication akhauri-etal-2024-shadowllm 10.18653/v1/2024.emnlp-main.1068 https://aclanthology.org/2024.emnlp-main.1068/ 2024-11 19154 19167