@article{cascadedmultigranularitypruningforondevi, title = {Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT}, author = {Jinghan Wang and Yanjun Chen and Wei Zhang and Xiaotong Huang and Tianchen Liu and Gaoliang Peng}, year = {2026}, eprint = {2606.26861}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.26861}, }