Algorithm/Software

Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC
通过细粒度算子融合重构私有 Transformer 推理的混合 CKKS/MPC 框架。
Tianshi Xu, Wenjie Lu, Jiangrui Yu, Chenqi Lin, Yi Chen, Runsheng Wang, 李萌
论文
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
Shuzhang Zhong, Yanfan Sun, Ling Liang, Runsheng Wang, Ru Huang, 李萌
论文
ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance
Tong Xie, Jiawang Zhao, Zishen Wan, Zuodong Zhang, Yuan Wang, Runsheng Wang, Ru Huang, 李萌
论文
SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
Linye Wei, Shuzhang Zhong, Songqiang Xu, Runsheng Wang, Ru Huang, 李萌
论文
SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings
Renjie Wei, Zechun Liu, Yuchen Fan, Runsheng Wang, Ru Huang, 李萌
论文
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
Renze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng, Xiuhong Li, Xuechao Wei, Shengen Yan, 李萌, Yun Liang
论文
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Tianshi Xu, Lemeng Wu, Runsheng Wang, 李萌
论文
AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
Shuzhang Zhong, Ling Liang, Yuan Wang, Runsheng Wang, Ru Huang, 李萌
论文
FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference
Jiangrui Yu, Wenxuan Zeng, Tianshi Xu, Renze Chen, Yun (Eric) Liang, Runsheng Wang, Ru Huang, 李萌
论文
MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers
Zebin Yang, Renze Chen, Taiqiang Wu, Ngai Wong, Yun (Eric) Liang, Runsheng Wang, Ru Huang, 李萌
论文