Portrait of Rongtian Fu

Rongtian Fu 付容天

Google Scholar rongtianfu@bupt.edu.cn rongtianfu@gmail.com
System for AI High-Performance Computing Parallel Computing

Biography

Rongtian Fu is currently a Ph.D. student at the Parallel Computing and Intelligent Systems Laboratory (ParCIS Lab), Beijing University of Posts and Telecommunications (BUPT), under the supervision of Prof. Shigang Li, starting from 2024. Prior to that, he received his B.S. degree in Computer Science from BUPT in 2024.

Publications

UltraGNN: A Sparse-Operator-Aware Framework for Accelerating Graph Neural Networks on Tensor Cores

TPDS 2026 Jinliang Shi, Shigang Li, Rongtian Fu, Xueying Wang, Youxuan Xu, Tong Wu
Paper Code

TwinCache: A Retrieval- and Reranking-Aware Caching System for Efficient RAG Serving

ATC 2026 Youxuan Xu, Rongtian Fu, Jinliang Shi, Tong Wu, Zhi Ma, Shigang Li

MX-KMeans: Accelerating K-Means Clustering through Microscaling Quantization

ICPP 2026 Rongtian Fu, Dongbo Lv, Xueying Wang, Shigang Li
Paper Code

Omnia: Efficient RAG Serving through Speculative Scheduling

HPDC 2026 Rongtian Fu, Shigang Li, Youxuan Xu, Tong Wu, Zhi Ma, Jinliang Shi
Paper Code

Dynamo-MoE: Accelerating Sparse Large Model Inference with Dynamic Parallelization

HPDC 2026 Jiahao Chen, Shigang Li, Rongtian Fu, Tong Wu, Zhi Ma, Jingkun Dong
Paper

FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores

PPoPP 2025 Jinliang Shi, Shigang Li, Youxuan Xu, Rongtian Fu, Xueying Wang, Tong Wu
Paper Code