@article{highthroughputllminferenceon, title = {High-Throughput LLM inference on Heterogeneous Clusters}, author = {Yi Xiong and Jinqi Huang and Wenjie Huang and Xuebing Yu and Entong Li and Zhixiong Ning and Jinhua Zhou and Li Zeng and Xin Chen}, year = {2025}, eprint = {2504.15303}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.15303v1}, }