Publications

publications in reversed chronological order.

2026

  1. ASPLOS ’26
    Towards High-Goodput LLM Serving with Prefill-decode Multiplexing
    Yukang Chen, Weihao Cui, Han Zhao, Ziyi Xu, Xiaoze Fan,  Xusheng Chen, Yangjie Zhou, Shixuan Sun, Bingsheng He, and Quan Chen
    In Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2026) 2026
  2. TACO ’26
    Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling
    Yifei Liu, Zuo Gan, Zhenghao Gan, Weiye Wang, Chen Chen, Yizhou Shan,  Xusheng Chen, Zhenhua Han, Yifei Zhu, Shixuan Sun, and Minyi Guo
    ACM Transactions on Architecture and Code Optimization 2026
  3. EuroSys ’26
    Lessons Learned from Incorporating Formal Methods in Huawei Cloud Reliability
    Claudia Cauli, Timo Lang, Shuo Chen, Sebti Mouelhi, Xin Jin, Subhajit Bandopadhyay,  Xusheng Chen, Yazhi Feng, Haoze Song , Linhua Tang, Zhenli Sheng, and Ananth Shrinivas Srinath
    In Proceedings of the 21st European Conference on Computer Systems (EuroSys 2026) 2026

2025

  1. Tech Report
    xDeepServe: Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
    XDS Team
    2025
  2. ATC ’25
    DeepServe: Serverless Large Language Model Serving at Scale
    Junhao Hu, Jiang Xu, Zhixia Liu, Yulong He, Yuetao Chen, Hao Xu, Jiang Liu, Jie Meng, Baoquan Zhang, Shining Wan, Gengyuan Dan, Zhiyu Dong, Zhihao Ren, Changhong Liu, Tao Xie, Dayun Lin, Qin Zhang, Yue Yu, Hao Feng,  Xusheng Chen, and Yizhou Shan
    In 2025 USENIX Annual Technical Conference (USENIX ATC 25) 2025
  3. ATC ’25
    Toppings: CPU-Assisted, Rank-Aware Adapter Serving for LLM Inference
    Suyi Li, Hanfeng Lu, Tianyuan Wu, Minchen Yu, Qizhen Weng,  Xusheng Chen, Yizhou Shan, Binhang Yuan, and Wei Wang
    In 2025 USENIX Annual Technical Conference (USENIX ATC 25) 2025
  4. ICML ’25
    EPIC: Efficient Position-Independent Caching for Serving Large Language Models
    Junhao Hu, Wenrui Huang, Weidong Wang, Haoyi Wang, Tiancheng Hu, Qin Zhang, Hao Feng,  Xusheng Chen, Yizhou Shan, and Tao Xie
    In Proceedings of the 42nd International Conference on Machine Learning (ICML 2025) 2025
  5. ACL ’25
    RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
    Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu,  Xusheng Chen, Tao Xie, and Yizhou Shan
    In Findings of the Association for Computational Linguistics (ACL 2025) 2025
  6. TACO ’25
    ShuffleInfer: Disaggregate LLM Inference for Mixed Downstream Workloads
    Cunchen Hu, Heyang Huang, Liangliang Xu,  Xusheng Chen, Chenxi Wang, Jiang Xu, Shuang Chen, Hao Feng, Sa Wang, Yungang Bao, Ninghui Sun, and Yizhou Shan
    ACM Transactions on Architecture and Code Optimization 2025
  7. SIGMOD ’25
    Perseus: Achieving Strong Consistency and High Data Freshness for Scalable Geo-distributed HTAP
    Haoze Song ,  Xusheng Chen, Ruijie Gong, Zekai Sun, Tianxiang Shen , Cheng Li , Hao Feng, Sen Wang, and Heming Cui
    Proceedings of the ACM on Management of Data (SIGMOD) 2025
  8. VLDB ’25
    K2: On Optimizing Distributed Transactions in a Multi-region Data Store with TrueTime Clocks
    Haoze Song , Yongqi Wang,  Xusheng Chen, Hao Feng, Yazhi Feng, Xieyun Fang, Heming Cui , and Linghe Kong
    Proceedings of the VLDB Endowment (PVLDB) 2025
  9. VLDB ’25
    FlatStor: An Efficient Embedded-Index Based Columnar Data Layout for Multimodal Data Workloads
    Chi Zhang, Shihao Zhang, Yunfei Gu, Chentao Wu, Jie Li, Qin Zhang,  Xusheng Chen, and Jie Meng
    Proceedings of the VLDB Endowment (PVLDB) 2025
  10. TPDS ’25
    PipeMesh: Achieving Memory-Efficient Computation-Communication Overlap for Training Large Language Models
    Fanxin Li , Shixiong Zhao , Yuhao Qing, Jianyu Jiang ,  Xusheng Chen, and Heming Cui
    IEEE Transactions on Parallel and Distributed Systems 2025
  11. TSC ’25
    SLARM: SLA-Aware, Reliable and Efficient Transaction Dissemination for Permissioned Blockchains
    Ji Qi , Tianxiang Shen , Jianyu Jiang ,  Xusheng Chen, Xiapu Luo , Fengwei Zhang , and Heming Cui
    IEEE Transactions on Services Computing 2025
  12. arXiv ’25
    Hecate: Unlocking Efficient Sparse Model Training via Fully Sharded Sparse Data Parallelism
    Yuhao Qing, Guichao Zhu, Fanxin Li , Lintian Lei, Zekai Sun, Xiuxian Guan , Shixiong Zhao ,  Xusheng Chen, Dong Huang, Sen Wang, and Heming Cui
    arXiv preprint arXiv:2502.02581 2025

2024

  1. arXiv ’24
    MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
    Cunchen Hu, Heyang Huang, Junhao Hu, Jiang Xu,  Xusheng Chen, Tao Xie, Chenxi Wang, Sa Wang, Yungang Bao, Ninghui Sun, and Yizhou Shan
    arXiv preprint arXiv:2406.17565 2024
  2. arXiv ’24
    The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving
    Pai Zeng, Zhenyu Ning, Jieru Zhao, Weihao Cui, Mengwei Xu, Liwei Guo,  Xusheng Chen, and Yizhou Shan
    arXiv preprint arXiv:2405.11299 2024

2023

  1. TPDS ’23
    Fold3D: Rethinking and Parallelizing Computational and Communicational Tasks in the Training of Large DNN Models
    Fanxin Li , Shixiong Zhao , Yuhao Qing,  Xusheng Chen, Xiuxian Guan , Sen Wang, Gong Zhang, and Heming Cui
    IEEE Transactions on Parallel and Distributed Systems 2023
  2. HotOS ’23
    Skadi: Building a Distributed Runtime for Data Systems in Disaggregated Data Centers
    Cunchen Hu, Chenxi Wang, Sa Wang, Ninghui Sun, Yungang Bao, Jieru Zhao, Sanidhya Kashyap, Pengfei Zuo,  Xusheng Chen, Liangliang Xu, Qin Zhang, Hao Feng, and Yizhou Shan
    In Proceedings of the 19th Workshop on Hot Topics in Operating Systems (HotOS 2023) 2023
  3. TSC ’23
    FRing: A Geography-Based P2P Overlay Network for Fast and Robust Blockchain Systems
    Haoran Qiu, Tao Ji, Shixiong Zhao ,  Xusheng Chen, Ji Qi , Heming Cui , and Sen Wang
    IEEE Transactions on Services Computing 2023
  4. IoT-J ’23
    COORP: Satisfying Low-Latency and High-Throughput Requirements of Wireless Network for Coordinated Robotic Learning
    Shengliang Deng, Xiuxian Guan , Zekai Sun, Shixiong Zhao , Tianxiang Shen ,  Xusheng Chen, Tianyang Duan, Yuexuan Wang , Jia Pan, Yanjun Wu, Libo Zhang, and Heming Cui
    IEEE Internet of Things Journal 2023

2022

  1. ATC ’22
    SOTER: Guarding Black-box Inference for General Neural Networks at the Edge
    Tianxiang Shen , Ji Qi , Jianyu Jiang , Xian Wang, Siyuan Wen,  Xusheng Chen, Shixiong Zhao , Sen Wang, Li Chen, Xiapu Luo , Fengwei Zhang , and Heming Cui
    In 2022 USENIX Annual Technical Conference (USENIX ATC 22) 2022
  2. MICRO ’22
    CRONUS: Fault-isolated, Secure and High-performance Heterogeneous Computing for Trusted Execution Environments
    Jianyu Jiang , Ji Qi , Tianxiang Shen ,  Xusheng Chen, Shixiong Zhao , Sen Wang, Li Chen, Gong Zhang, Xiapu Luo , and Heming Cui
    In 2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO) 2022
  3. MICRO ’22
    ROG: A High Performance and Robust Distributed Training System for Robotic IoT
    Xiuxian Guan , Zekai Sun, Shengliang Deng,  Xusheng Chen, Shixiong Zhao , Zongyuan Zhang, Tianyang Duan, Yuexuan Wang , Chengshu Wu, Yong Cui, Libo Zhang, Rui Wang, and Heming Cui
    In 2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO) 2022
  4. SIGMETRICS ’22
    Efficient and DoS-resistant Consensus for Permissioned Blockchains
    Xusheng Chen, Shixiong Zhao , Ji Qi , Jianyu Jiang , Haoze Song , Cheng Wang , Tsz On Li , TH Hubert Chan , Fengwei Zhang , Xiapu Luo , Sen Wang, Gong Zhang, and Heming Cui
    ACM SIGMETRICS Performance Evaluation Review / Performance Evaluation 2022
  5. ASPLOS ’22
    NASPipe: High Performance and Reproducible Pipeline Parallel Supernet Training via Causal Synchronous Parallelism
    Shixiong Zhao , Fanxin Li ,  Xusheng Chen, Tianxiang Shen , Li Chen, Sen Wang, Nicholas Zhang, Cheng Li , and Heming Cui
    In Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2022) 2022
  6. TDSC ’22
    DAENet: Making Strong Anonymity Scale in a Fully Decentralized Network
    Tianxiang Shen , Jianyu Jiang , Yunpeng Jiang,  Xusheng Chen, Ji Qi , Shixiong Zhao , Fengwei Zhang , Xiapu Luo , and Heming Cui
    IEEE Transactions on Dependable and Secure Computing 2022
  7. TPDS ’22
    vPipe: A Virtualized Acceleration System for Achieving Efficient and Scalable Pipeline Parallel DNN Training
    Shixiong Zhao , Fanxin Li ,  Xusheng Chen, Xiuxian Guan , Jianyu Jiang , Dong Huang, Yuhao Qing, Sen Wang, Peng Wang, Gong Zhang, Cheng Li , Ping Luo, and Heming Cui
    IEEE Transactions on Parallel and Distributed Systems 2022

2021

  1. SOSP ’21
    BIDL: A High-throughput, Low-latency Permissioned Blockchain Framework for Datacenter Networks
    Ji Qi* ,  Xusheng Chen*, Yunpeng Jiang, Jianyu Jiang , Tianxiang Shen , Shixiong Zhao , Sen Wang, Gong Zhang, Li Chen, Man Ho Au , and Heming Cui
    *Parallel First Author, equal contribution.
    In Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (SOSP) 2021
  2. EuroSys ’21
    Achieving Low Tail-latency and High Scalability for Serializable Transactions in Edge Computing
    Xusheng Chen, Haoze Song , Jianyu Jiang , Chaoyi Ruan, Cheng Li , Sen Wang, Gong Zhang, Reynold Cheng , and Heming Cui
    In Proceedings of the Sixteenth European Conference on Computer Systems (EuroSys) 2021

2020

  1. DSN ’20
    HAMS: High Availability for Distributed Machine Learning Service Graphs
    Shixiong Zhao* ,  Xusheng Chen*, Cheng Wang , Fanxin Li , Qi Ji, Heming Cui , Cheng Li , and Sen Wang
    *Parallel First Author, equal contribution.
    In 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) 2020
  2. DSN ’20
    UPA: An Automated, Accurate and Efficient Differentially Private Big-data Mining System
    Tsz On Li , Jianyu Jiang , Ji Qi , Chi Chiu So, Jiacheng Ma,  Xusheng Chen, Tianxiang Shen , Heming Cui , Yuexuan Wang , and Peng Wang
    In 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) 2020
  3. AsiaCCS ’20
    Uranus: Simple, Efficient SGX Programming and its Applications
    Jianyu Jiang ,  Xusheng Chen, Tsz On Li , Cheng Wang , Tianxiang Shen , Shixiong Zhao , Heming Cui , Cho-Li Wang , and Fengwei Zhang
    In Proceedings of the 15th ACM Asia Conference on Computer and Communications Security (AsiaCCS) 2020

2019

  1. SRDS ’19
    Fulva: Efficient Live Migration for In-Memory Key-Value Stores with Zero Downtime
    Jiewen Hai, Cheng Wang ,  Xusheng Chen, Tsz On Li , Heming Cui , and Sen Wang
    In 2019 38th Symposium on Reliable Distributed Systems (SRDS) 2019

2018

  1. NSDI ’18
    PLOVER: Fast, Multi-core Scalable Virtual Machine Fault-tolerance
    Cheng Wang* ,  Xusheng Chen*, Weiwei Jia, Boxuan Li, Haoran Qiu, Shixiong Zhao , and Heming Cui
    *Parallel First Author, equal contribution.
    In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18) 2018
  2. ATC ’18
    Effectively Mitigating I/O Inactivity in vCPU Scheduling
    Weiwei Jia, Cheng Wang ,  Xusheng Chen, Jianchen Shan, Xiaowei Shang, Heming Cui , Xiaoning Ding, Luwei Cheng, Francis C. M. Lau, Yuexuan Wang , and Yuangang Wang
    In 2018 USENIX Annual Technical Conference (USENIX ATC 18) 2018

2017

  1. SoCC ’17
    APUS: Fast and Scalable Paxos on RDMA
    Cheng Wang , Jianyu Jiang ,  Xusheng Chen, Ning Yi, and Heming Cui
    In Proceedings of the 2017 Symposium on Cloud Computing (SoCC) 2017
  2. ICPADS ’17
    A Fast, General Storage Replication Protocol for Active-Active Virtual Machine Fault Tolerance
    Cheng Wang ,  Xusheng Chen, Zixu Wang, Youwei Zhu, and Heming Cui
    In 2017 IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS) 2017