publications

2026

  1. EuroSys
    High Throughput and Low Latency LLM Serving via Adaptive KV Caching
    Wenyan Chen, Chengzhi Lu, Kejiang Ye, Huanle Xu, and Chengzhong Xu
    In proceedings of European Conference on Computer Systems, 2026
  2. INFOCOM
    FedSUV: Validity and Utility-guided Client Selection for Federated Learning
    Xiaosong Chen, Wenyan Chen, Yuanhang Chen, and Huanle Xu
    In proceedings of IEEE International Conference on Computer Communications, 2026

2025

  1. SoCC
    FedDance: Efficient Participant Selection for Federated Learning in Highly Dynamic Environments
    Yuanhang Chen, Xiaosong Chen, Wenyan Chen, and Huanle Xu
    In proceedings of the annual ACM Symposium on Cloud Computing, 2025
  2. EuroSys
    Multiplexing Dynamic Deep Learning Workloads with SLO-awareness in GPU Clusters
    Wenyan Chen, Chengzhi Lu, Huanle Xu, Kejiang Ye, and Chengzhong Xu
    In proceedings of European Conference on Computer Systems, 2025
    DOI PDF Slides

2024

  1. SC
    SMIless: Serving DAG-based Inference with Dynamic Invocations under Serverless Computing
    Chengzhi Lu, Huanle Xu, Yudan Li, Wenyan Chen, Kejiang Ye, and Chengzhong Xu
    In proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, 2024
    DOI PDF
  2. CSCWD
    EINS: Edge-Cloud Deep Model Inference with Network-Efficiency Schedule in Serverless
    Shijie Peng, Yanying Lin, Wenyan Chen, Yingfei Tang, Xu Duan, and Kejiang Ye
    In proceedings of the International Conference on Computer Supported Cooperative Work in Design, 2024
    DOI PDF

2023

  1. SC
    Interference-aware multiplexing for deep learning in gpu clusters: A middleware approach
    Wenyan Chen, Zizhao Mo, Huanle Xu, Kejiang Ye, and Chengzhong Xu
    In proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, 2023
    DOI PDF Code Slides

2021

  1. CLUSTER
    Rptcn: Resource prediction for high-dynamic workloads in clouds based on deep learning
    Wenyan Chen, Chengzhi Lu, Kejiang Ye, Yang Wang, and Chengzhong Xu
    In proceedings of IEEE International Conference on Cluster Computing, 2021
    DOI PDF

2020

  1. HPCC
    HySync: Hybrid federated learning with effective synchronization
    Guomei Shi, Li Li, Jun Wang, Wenyan Chen, Kejiang Ye, and Chengzhong Xu
    In proceedings of IEEE International Conference on High Performance Computing & Communications, 2020
    DOI PDF
  2. HDIS
    Understanding the workload characteristics in alibaba: A view from directed acyclic graph analysis
    Chengzhi Lu, Wenyan Chen, Kejiang Ye, and Chengzhong Xu
    In proceedings of International Conference on High Performance Big Data and Intelligent Systems, 2020
    DOI PDF
  3. JCST
    Interference analysis of co-located container workloads: a perspective from hardware performance counters
    Wenyan Chen, Kejiang Ye, Chengzhi Lu, Dongdai Zhou, and Chengzhong Xu
    Journal of Computer science and Technology, 2020
    DOI PDF

2019

  1. HPCC
    Co-locating online workload and offline workload in the cloud: An interference analysis
    Wenyan Chen, Kejiang Ye, and Chengzhong Xu
    In proceedings of IEEE International Conference on High Performance Computing & Communications, 2019
    DOI PDF
  2. ICPADS
    Adgs: Anomaly detection and localization based on graph similarity in container-based clouds
    Chengzhi Lu, Kejiang Ye, Wenyan Chen, and Chengzhong Xu
    In proceedings of the IEEE International Conference on Parallel and Distributed Systems, 2019
    DOI PDF

2018

  1. ICPADS
    How does the workload look like in production cloud? analysis and clustering of workloads on alibaba cluster trace
    Wenyan Chen, Kejiang Ye, Yang Wang, Guoyao Xu, and Chengzhong Xu
    In proceedings of the IEEE International Conference on Parallel and Distributed Systems, 2018
    DOI PDF