Liangkun Chen

According to our database, Liangkun Chen authored at least 2 papers between 2024 and 2025.

Collaborative distances:

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

2025

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference.

Liangkun Chen, Zijian Wen, Tian Wu, Xiaoxi Zhang, Chuan Wu

CoRR, October, 2025

2024

Alleviating All-to-All Communication for Deep Learning Recommendation Model Inference.

Songjun Huang, Yihong Li, Liangkun Chen, Xiaoxi Zhang, Shuo Liu, Jingpu Duan, Wenfei Wu, Xu Chen

Proceedings of the Workshop Proceedings of the 53rd International Conference on Parallel Processing, 2024