@article{chunkllmalightweightpluggableframeworkfo, title = {ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference}, author = {Haojie Ouyang and Jianwei Lv and Lei Ren and Chen Wei and Xiaojie Wang and Fangxiang Feng}, year = {2025}, eprint = {2510.02361}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.02361}, }