Shenggan Cheng

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 18

Top Topics

Memory Efficient

Inference Process

Top Venues

Publications

Ziming Liu, Shaoyu Wang, Shenggan Cheng, Zhongkai Zhao, Xuanlei Zhao, James Demmel, Yang You
WallFacer: Guiding Transformer Model Training Out of the Long-Context Dark Forest with N-body Problem. CoRR (2024)
Shenggan Cheng, Xuanlei Zhao, Guangyang Lu, Jiarui Fang, Tian Zheng, Ruidong Wu, Xiwen Zhang, Jian Peng, Yang You
FastFold: Optimizing AlphaFold Training and Inference on GPU Clusters. PPoPP (2024)
Xuanlei Zhao, Shenggan Cheng, Guangyang Lu, Haotian Zhou, Bin Jia, Yang You
AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference. ICLR (2024)
Xuanlei Zhao, Shenggan Cheng, Zangwei Zheng, Zheming Yang, Ziming Liu, Yang You
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers. CoRR (2024)
Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, Yang You
HeteGen: Efficient Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices. MLSys (2024)
Xuanlei Zhao, Shenggan Cheng, Guangyang Lu, Jiarui Fang, Haotian Zhou, Bin Jia, Ziming Liu, Yang You
AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference. CoRR (2024)
Jiangsu Du, Jinhui Wei, Jiazhi Jiang, Shenggan Cheng, Dan Huang, Zhiguang Chen, Yutong Lu
Liger: Interleaving Intra- and Inter-Operator Parallelism for Distributed Large Model Inference. PPoPP (2024)
Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, Yang You
HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices. CoRR (2024)
Ziming Liu, Shenggan Cheng, Haotian Zhou, Yang You
Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency. CoRR (2023)
Shenggan Cheng, Ziming Liu, Jiangsu Du, Yang You
ATP: Adaptive Tensor Parallelism for Foundation Models. CoRR (2023)
Ziming Liu, Shenggan Cheng, Haotian Zhou, Yang You
Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency. SC (2023)
Shenggan Cheng, Ruidong Wu, Zhongming Yu, Bin-Rui Li, Xiwen Zhang, Jian Peng, Yang You
FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours. CoRR (2022)
Bin-Rui Li, Shenggan Cheng, James Lin
tcFFT: Accelerating Half-Precision FFT through Tensor Cores. CoRR (2021)
Bin-Rui Li, Shenggan Cheng, James Lin
tcFFT: A Fast Half-Precision FFT Library for NVIDIA Tensor Cores. CLUSTER (2021)
Shenggan Cheng, Hao-Ran Yu, Derek Inman, Qiucheng Liao, Qiaoya Wu, James Lin
CUBE - Towards an Optimal Scaling of Cosmological N-body Simulations. CCGRID (2020)
Shenggan Cheng, Hao-Ran Yu, Derek Inman, Qiucheng Liao, Qiaoya Wu, James Lin
CUBE - Towards an Optimal Scaling of Cosmological N-body Simulations. CoRR (2020)
Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li
HMS-Net: Hierarchical Multi-Scale Sparsity-Invariant Network for Sparse Depth Completion. IEEE Trans. Image Process. 29 (2020)
Kunyuan Du, Ya Zhang, Haibing Guan, Qi Tian, Yanfeng Wang, Shenggan Cheng, James Lin
FTL: A Universal Framework for Training Low-Bit DNNs via Feature Transfer. ECCV (25) (2020)