Jinliang Shi

[SC '26] Jinliang Shi, Shigang Li

FastInfer: Breaking the Low-to-Moderate Sparsity Barrier for Efficient LLM Inference

[CCF-A] [Code]

[TPDS '26] Jinliang Shi, Shigang Li, Rongtian Fu, Xueying Wang, Youxuan Xu, Tong Wu

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

[CCF-A] [Code]

[PPoPP '25] Jinliang Shi, Shigang Li, Youxuan Xu, Rongtian Fu, Xueying Wang, Tong Wu

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

[CCF-A] [Paper] [Code]

[Parallel Computing '23] Jinliang Shi, Dewu Chen, Jiabi Liang, Lin Li, Yue Lin, Jianjiang Li

New YARN sharing GPU based on graphics memory granularity scheduling

[CCF-B] [Paper]

[Under Evaluation] Jinliang Shi, Shigang Li, Youxuan Xu, Xueying Wang, Rongtian Fu, Zhi Ma, Tong Wu

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication

[Paper] [Code]

[HPDC '26] Rongtian Fu, Shigang Li, Youxuan Xu, Tong Wu, Zhi Ma, and Jinliang Shi

Omnia: Efficient RAG Serving through Speculative Scheduling

[CCF-A] [Paper]

[Parallel Computing '24] Jianjiang Li, Lin Li, Qingwei Wang, Wei Xue, Jiabi Liang, and Jinliang Shi

Parallel Optimization and Application of Unstructured Sparse Triangular Solver on New Generation of Sunway Architecture

[CCF-B] [Paper]