@article{semanticschedulingforllminference, title = {Semantic Scheduling for LLM Inference}, author = {Wenyue Hua and Dujian Ding and Yile Gu and Yujie Ren and Kai Mei and Minghua Ma and William Yang Wang}, year = {2025}, eprint = {2506.12204}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.12204v1}, }