Xinfeng Xia

According to our database, Xinfeng Xia authored at least 5 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts.

Wenfeng Wang, Jiacheng Liu, Xiaofeng Hou, Xinfeng Xia, Peng Tang, Mingxuan Zhang, Chao Li, Minyi Guo

CoRR, November, 2025

MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs.

Xinfeng Xia, Jiacheng Liu, Xiaofeng Hou, Peng Tang, Mingxuan Zhang, Wenfeng Wang, Chao Li

CoRR, October, 2025

MMBypass: Towards efficient multi-modal AI computing with adaptive bypass network.

Yifei Pu, Xinfeng Xia, Xiaofeng Hou, Chi Wang, Cheng Xu, Jiacheng Liu, Jing Wang, Minyi Guo, Jingling Yuan, Chao Li

J. Parallel Distributed Comput., 2025

2024

Sub-model Parallelism: A Scale-out Deployment Method for Large Multi-modal DNNs.

Tianhao Huang, Lingyu Sun, Xiaofeng Hou, Xiaozhi Zhu, Xinfeng Xia, Yutong Wang, Mingxi Chen, Chao Li

Proceedings of the 24th IEEE International Symposium on Cluster, 2024

2021

Study of Experimental Teaching Mode Based on OBE.

Xinfeng Xia, Weiwei Lv

Proceedings of the 10th International Conference on Educational and Information Technology, 2021