代表性学术论文
JanusQuant被CCF A类会议PPoPP2026 接收!
ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, 2026,CCF体系结构A类会议
JanusQuant: Accurate and Efficient 2-bit KV Cache Quantization for Long-context Inference
IEEE TPDS 2024 Best Paper Runner-Up
"MPMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism" 荣获CCF-A类期刊IEEE TPDS 2024 Best Paper Runner-Up!
2篇论文被SC'25接收!
The International Conference for High Performance Computing, Networking, Storage, and Analysis 2025,CCF体系结构A类会议
HyTiS: Hybrid Tile Scheduling for GPU GEMM with Enhanced Wave Utilization and Cache Locality
MXBLAS: Accelerating 8-bit Deep Learning with a Unified Micro-Scaled GEMM Library
2篇论文分别被ICDE'25和USENIX ATC'25接收!
IEEE International Conference on Data Engineering,CCF A类会议
USENIX Annual Technical Conference,CCF A类会议
2篇论文分别被WWW'25和CHI'25接收!
International World Wide Web Conference,CCF A类会议
ACM Conference on Human Factors in Computing Systems,CCF A类会议