RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference

RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference Yige Xu author Xu Guo author Zhiwei Zeng author Chunyan Miao 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 xu-etal-2024-revmux 10.18653/v1/2024.emnlp-main.1232 https://aclanthology.org/2024.emnlp-main.1232/ 2024-11 22072 22087