publications

Publications in reversed chronological order.

  1. ___EuroSys___
    Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
    Yu, Hanfei, Cui, Xingqi, Zhang, Hong, Wang, Hao, and Wang, Hao
    In EuroSys 2026
    1. ___HotNets___
      Toward Data-Centric Service Composition
      Fu, Silvery, Zhang, Hong, Teoh, Ryan, Priadka, Taras, and Ratnasamy, Sylvia
      In HotNets 2024
    2. ___ASPLOS___
      RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Cachine and Sharing
      Yu, Hanfei, Roy, Rohan Basu, Fontenot, Christian, Tiwari, Devesh, Li, Jian, Zhang, Hong, Wang, Hao, and Park, Seung-Jong
      In ASPLOS 2024
    3. ___EuroSys___
      Accelerating Privacy-Preserving Machine Learning with GeniBatch
      Huang, Xinyang, Zhang, Junxue, Cheng, Xiaodian, Zhang, Hong, Jin, Yilun, Hu, Shuihai, Tian, Han, and Chen, Kai
      In EuroSys 2024
    1. _____NSDI_____
      SHEPHERD: Serving DNNs in the Wild
      Zhang, Hong, Tang, Yupeng, Khandelwal, Anurag, and Stoica, Ion
      In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, 2023
      PDF
    1. ___HotNets___
      The Internet of Things in a Laptop: Rapid Prototyping for IoT Applications with Digibox
      Fu, Silvery, Zhang, Hong, Ratnasamy, Sylvia, and Stoica, Ion
      In HotNets 2022
      PDF
    2. _____NSDI_____
      NetHint: White-Box Networking for Multi-Tenant Data Centers
      Chen, Jingrong, Zhang, Hong, Zhang, Wei, Luo, Liang, Chase, Jeffery, Stoica, Ion, and Zhuo, Danyang
      In Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation, 2022
      PDF
    3. __SIGCOMM__
      LiteFlow: Towards High-performance Adaptive Neural Networks for Kernel Datapath
      Zhang, Junxue, Zeng, Chaoliang, Zhang, Hong, Hu, Shuihai, and Chen, Kai
      In Proceedings of the ACM SIGCOMM 2022 Conference, 2022
      PDF
    1. _____NSDI_____
      Caerus: NIMBLE Task Scheduling for Serverless Analytics
      Zhang, Hong, Tang, Yupeng, Khandelwal, Anurag, Chen, Jingrong, and Stoica, Ion
      In Proceedings of the 18th USENIX Symposium on Networked Systems Design and Implementation, 2021
      PDF
    1. ____APNet____
      RAT - Resilient Allreduce Tree for Distributed Machine Learning
      Wan, Xinchen, Zhang, Hong, Wang, Hao, Hu, Shuihai, Zhang, Junxue, and Chen, Kai
      In Proceedings of the 4th Asia-Pacific Workshop on Networking, 2020
      PDF
      1. ____APNet____
        Pas de Deux: Shape the Circuits, and Shape the Apps Too!
        Zhang, Hong, Chen, Kai, and Chowdhury, Mosharaf
        In Proceedings of the 2nd Asia-Pacific Workshop on Networking, 2018
        PDF
      1. __SIGCOMM__
        Resilient Datacenter Load Balancing in the Wild
        Zhang, Hong, Zhang, Junxue, Bai, Wei, Chen, Kai, and Chowdhury, Mosharaf
        In Proceedings of the ACM SIGCOMM 2017 Conference, 2017
        PDF
      2. _____ToN_____
        Guaranteeing Deadlines for Inter-Datacenter Transfers
        Zhang, Hong, Chen, Kai, Bai, Wei, Han, Dongsu, Tian, Chen, Wang, Hao, Guan, Haibin, and Zhang, Ming
        IEEE/ACM Transactions on Networking, 2017
        PDF
      1. __SIGCOMM__
        CODA: Toward Automatically Identifying and Scheduling Coflows in the Dark
        Zhang, Hong, Chen, Li, Yi, Bairen, Chen, Kai, Chowdhury, Mosharaf, and Geng, Yanhui
        In Proceedings of the ACM SIGCOMM 2016 Conference, 2016
        PDF
      2. ______TC______
        A Framework for Truthful Online Auctions in Cloud Computing with Heterogeneous User Demands
        Zhang, Hong, Jiang, Hongbo, Li, Bo, Liu, Fangming, Vasilakos, A., and Jiangchuan, Liu
        IEEE/ACM Transactions on Computers, 2016
        PDF
      1. ___EuroSys___
        Guaranteeing Deadlines for Inter-Datacenter Transfers
        Zhang, Hong, Chen, Kai, Bai, Wei, Han, Dongsu, Tian, Chen, Wang, Hao, Guan, Haibin, and Zhang, Ming
        In Proceedings of the 10th European Conference on Computer Systems, 2015
        PDF
      1. __INFOCOM___
        A Framework for Truthful Online Auctions in Cloud Computing with Heterogeneous User Demands
        Zhang, Hong, Li, Bo, Jiang, Hongbo, Liu, Fangming, Vasilakos, A., and Jiangchuan, Liu
        In Proceedings of the 32nd Annual IEEE International Conference on Computer Communications 2013
        PDF