Alert button
Picture for Ao Zhou

Ao Zhou

Alert button

FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission

Mar 01, 2024
Zeling Zhang, Dongqi Cai, Yiran Zhang, Mengwei Xu, Shangguang Wang, Ao Zhou

Viaarxiv icon

Architectural Implications of GNN Aggregation Programming Abstractions

Oct 21, 2023
Yingjie Qi, Jianlei Yang, Ao Zhou, Tong Qiao, Chunming Hu

Figure 1 for Architectural Implications of GNN Aggregation Programming Abstractions
Figure 2 for Architectural Implications of GNN Aggregation Programming Abstractions
Figure 3 for Architectural Implications of GNN Aggregation Programming Abstractions
Figure 4 for Architectural Implications of GNN Aggregation Programming Abstractions
Viaarxiv icon

EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models

Aug 28, 2023
Rongjie Yi, Liwei Guo, Shiyun Wei, Ao Zhou, Shangguang Wang, Mengwei Xu

Viaarxiv icon

Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms

Mar 20, 2023
Ao Zhou, Jianlei Yang, Yingjie Qi, Yumeng Shi, Tong Qiao, Weisheng Zhao, Chunming Hu

Figure 1 for Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms
Figure 2 for Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms
Figure 3 for Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms
Figure 4 for Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms
Viaarxiv icon

Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices

Jun 15, 2022
Rongjie Yi, Ting Cao, Ao Zhou, Xiao Ma, Shangguang Wang, Mengwei Xu

Figure 1 for Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices
Figure 2 for Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices
Figure 3 for Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices
Figure 4 for Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices
Viaarxiv icon

A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices

Feb 14, 2022
Qiyang Zhang, Xiang Li, Xiangying Che, Xiao Ma, Ao Zhou, Mengwei Xu, Shangguang Wang, Yun Ma, Xuanzhe Liu

Figure 1 for A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices
Figure 2 for A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices
Figure 3 for A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices
Figure 4 for A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices
Viaarxiv icon

Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms

Apr 12, 2021
Ao Zhou, Jianlei Yang, Yeqi Gao, Tong Qiao, Yingjie Qi, Xiaoyi Wang, Yunli Chen, Pengcheng Dai, Weisheng Zhao, Chunming Hu

Figure 1 for Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
Figure 2 for Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
Figure 3 for Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
Figure 4 for Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
Viaarxiv icon

Hierarchical Federated Learning through LAN-WAN Orchestration

Oct 22, 2020
Jinliang Yuan, Mengwei Xu, Xiao Ma, Ao Zhou, Xuanzhe Liu, Shangguang Wang

Figure 1 for Hierarchical Federated Learning through LAN-WAN Orchestration
Figure 2 for Hierarchical Federated Learning through LAN-WAN Orchestration
Figure 3 for Hierarchical Federated Learning through LAN-WAN Orchestration
Figure 4 for Hierarchical Federated Learning through LAN-WAN Orchestration
Viaarxiv icon

DP-Net: Dynamic Programming Guided Deep Neural Network Compression

Mar 21, 2020
Dingcheng Yang, Wenjian Yu, Ao Zhou, Haoyuan Mu, Gary Yao, Xiaoyi Wang

Figure 1 for DP-Net: Dynamic Programming Guided Deep Neural Network Compression
Figure 2 for DP-Net: Dynamic Programming Guided Deep Neural Network Compression
Figure 3 for DP-Net: Dynamic Programming Guided Deep Neural Network Compression
Figure 4 for DP-Net: Dynamic Programming Guided Deep Neural Network Compression
Viaarxiv icon