@article{servinglargelanguagemodelsonhuawei, title = {Serving Large Language Models on Huawei CloudMatrix384}, author = {Pengfei Zuo and Huimin Lin and Junbo Deng and Nan Zou and Xingkun Yang and Yingyu Diao and Weifeng Gao and Ke Xu and Zhangyu Chen and Shirui Lu and Zhao Qiu and Peiyang Li and Xianyu Chang and Zhengzhong Yu and Fangzheng Miao and Jia Zheng and Ying Li and Yuan Feng and Bei Wang and Zaijian Zong and Mosong Zhou and Wenli Zhou and Houjiang Chen and Xingyu Liao and Yipeng Li and Wenxiao Zhang and Ping Zhu and Yinggang Wang and Chuanjie Xiao and Depeng Liang and Dong Cao and Juncheng Liu and Yongqiang Yang and Xiaolong Bai and Yi Li and Huaguo Xie and Huatao Wu and Zhibin Yu and Lv Chen and Hu Liu and Yujun Ding and Haipei Zhu and Jing Xia and Yi Xiong and Zhou Yu and Heng Liao}, year = {2025}, eprint = {2506.12708}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.12708v3}, }