Jihao Xin, Tian Lyu, Qilong Pan 0001, Kesen Wang, Marco Canini. Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs. In Proceedings of the Sixth European Workshop on Machine Learning and Systems, EuroMLSys 2026, Edinburgh, Scotland, UK, April 27-30, 2026. pages 49-59, ACM, 2026. [doi]
Abstract is missing.