publications

2026

1. SIGCOMM26

   Connex: Endpoint Mobility Primitives for Dynamic LLM Serving

   Yanying Lin, Vincent Liu, Tao Luo, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the ACM SIGCOMM Conference, 2026

   Bib HTML PDF Slides

   @inproceedings{lin2026connex,
     title = {Connex: Endpoint Mobility Primitives for Dynamic LLM Serving},
     author = {Lin, Yanying and Liu, Vincent and Luo, Tao and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the ACM SIGCOMM Conference},
     year = {2026},
   }

2. ISCA26

   DynoPipe: Heterogeneous Edge-Cloud LLM Serving with Dynamically Orchestrated Pipeline Boundaries

   Yanying Lin, Baicheng Chen, Xinyu Zhang, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 53rd International Symposium on Computer Architecture, 2026

   Bib HTML PDF Slides

   @inproceedings{lin2026dynopipe,
     title = {DynoPipe: Heterogeneous Edge-Cloud LLM Serving with Dynamically Orchestrated Pipeline Boundaries},
     author = {Lin, Yanying and Chen, Baicheng and Zhang, Xinyu and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the 53rd International Symposium on Computer Architecture},
     year = {2026},
   }

3. TPDS26

   Workload-Adapted Resource Allocation for LLM Distributed Serving in Serverless Clusters

   Yanying Lin, Shijie Peng, Yanbo Li, Shutian Luo, Haiying Shen, Kejiang Ye, and Chengzhong Xu

   IEEE Transactions on Parallel and Distributed Systems, 2026

   Bib

   @article{lin2026workload,
     title = {Workload-Adapted Resource Allocation for LLM Distributed Serving in Serverless Clusters},
     author = {Lin, Yanying and Peng, Shijie and Li, Yanbo and Luo, Shutian and Shen, Haiying and Ye, Kejiang and Xu, Chengzhong},
     journal = {IEEE Transactions on Parallel and Distributed Systems},
     year = {2026},
   }

4. EuroSys26

   FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters

   Yanying Lin, Shijie Peng, Chengzhi Lu, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 21st European Conference on Computer Systems, 2026

   Insight Bib HTML PDF

   Insight: We find that for pipeline inference, the optimal online pipeline structure varies greatly depending on the incoming request distribution. Longer pipelines can absorb load spikes by dispersing demand, while shorter pipelines reduce communication overhead. Dynamically adjusting the pipeline structure according to the request distribution is an effective approach in serverless environments.

   @inproceedings{lin2026flexpipe,
     title = {FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters},
     author = {Lin, Yanying and Peng, Shijie and Lu, Chengzhi and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the 21st European Conference on Computer Systems},
     year = {2026},
   }

5. ICPP26

   ReliefServe: Relieving GPU Pressure in Multi-Model Serving via Selective CPU Escape

   Shijie Peng, Yanying Lin^*, Chengzhi Lu, Shuaipeng Wu, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 55th IEEE International Conference on Parallel Processing, 2026

   Bib

   @inproceedings{peng2026reliefserve,
     title = {ReliefServe: Relieving GPU Pressure in Multi-Model Serving via Selective CPU Escape},
     author = {Peng, Shijie and Lin, Yanying and Lu, Chengzhi and Wu, Shuaipeng and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the 55th IEEE International Conference on Parallel Processing},
     year = {2026},
   }

2025

1. SoCC25

   Understanding Diffusion Model Serving in Production: A Top-Down Analysis of Workload, Scheduling, and Resource Efficiency

   Yanying Lin, Shuaipeng Wu, Shutian Luo, Hong Xu, Haiying Shen, Chong Ma, Min Shen, Le Chen, Chengzhong Xu, Lin Qu, and Kejiang Ye

   In Proceedings of the 2025 ACM Symposium on Cloud Computing, 2025

   Insight Bib PDF Slides

   Insight: The main insights of this work are obtained from production systems. It focuses on the performance of online inference, middleware, and hardware layers, as well as the relationships between these three components. We find that skewed request distributions force systems to stress network and cache layers, resulting in poor resource locality and reduced system performance.

   @inproceedings{lin2025understanding,
     title = {Understanding Diffusion Model Serving in Production: A Top-Down Analysis of Workload, Scheduling, and Resource Efficiency},
     author = {Lin, Yanying and Wu, Shuaipeng and Luo, Shutian and Xu, Hong and Shen, Haiying and Ma, Chong and Shen, Min and Chen, Le and Xu, Chengzhong and Qu, Lin and Ye, Kejiang},
     booktitle = {Proceedings of the 2025 ACM Symposium on Cloud Computing},
     pages = {1--15},
     year = {2025},
   }

2. Cluster25

   ROCK: Serving Multimodal Model in Cloud with Heterogeneous-Aware Resource Orchestration for Thousands of LoRA Adapters

   Shuaipeng Wu, Yanying Lin^*, Shijie Peng, Yanbo Li, Wenyan Chen, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 2025 IEEE International Conference on Cluster Computing, 2025

   Insight Bib PDF

   Insight: This work analyzes the performance of different request workloads in production-level environments and proposes a heterogeneous graph matching algorithm to adapt to different levels of resource characteristics and inference performance of various workloads. ROCK is a system-level resource orchestration framework designed to optimize the deployment of thousands of LoRA adapters in a cloud environment through intelligent resource allocation and workload-aware scheduling.

   @inproceedings{wu2025rock,
     title = {ROCK: Serving Multimodal Model in Cloud with Heterogeneous-Aware Resource Orchestration for Thousands of LoRA Adapters},
     author = {Wu, Shuaipeng and Lin, Yanying and Peng, Shijie and Li, Yanbo and Chen, Wenyan and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the 2025 IEEE International Conference on Cluster Computing},
     year = {2025},
   }

3. IEEE TSC25

   Serving LLM in Distributed GPU Cluster with Fine-Grain Pipeline Constraints

   Yanying Lin, Shijie Peng, Shuaipeng Wu, Yanbo Li, Chengzhi Lu, Kejiang Ye, and Chengzhong Xu

   IEEE Transactions on Services Computing, 2025

   Insight Bib

   Insight: LLMs are increasingly deployed in distributed GPU clusters using pipeline parallelism for efficient inference. However, existing approaches treat the entire pipeline as a monolithic unit, resulting in coarse-grained resource management and suboptimal SLO compliance. Each pipeline stage has distinct workload characteristics, but current systems cannot leverage this for better performance control. We propose fine-grained pipeline constraints that manage each stage independently, enabling precise SLO allocation at the stage level.

   @article{lin2025serving,
     title = {Serving LLM in Distributed GPU Cluster with Fine-Grain Pipeline Constraints},
     author = {Lin, Yanying and Peng, Shijie and Wu, Shuaipeng and Li, Yanbo and Lu, Chengzhi and Ye, Kejiang and Xu, Chengzhong},
     journal = {IEEE Transactions on Services Computing},
     year = {2025},
   }

2024

1. ICDCS24

   Quart: Latency-Aware FaaS System for Pipelining Large Model Inference

   Yanying Lin, Yanbo Li, Shijie Peng, Yingfei Tang, Shutian Luo, Haiying Shen, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 44th IEEE International Conference on Distributed Computing Systems, 2024

   Insight Bib PDF

   Insight: We find that when using pipeline inference for LLMs, each stage exhibits significant load differences due to varying resource allocation and throughput across different workloads. For example, under stable or bursty traffic patterns, throughput disparities between upstream and downstream stages can create performance-critical bottlenecks in the pipeline.

   @inproceedings{lin2024quart,
     title = {Quart: Latency-Aware FaaS System for Pipelining Large Model Inference},
     author = {Lin, Yanying and Li, Yanbo and Peng, Shijie and Tang, Yingfei and Luo, Shutian and Shen, Haiying and Xu, Chengzhong and Ye, Kejiang},
     booktitle = {Proceedings of the 44th IEEE International Conference on Distributed Computing Systems},
     year = {2024},
   }

2. ICWS24

   Plank: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint

   Yanying Lin, Shijie Peng, Shuaipeng Wu, Yanbo Li, Chengzhi Lu, Chengzhong Xu, and Kejiang Ye

   In Proceedings of the 31st IEEE International Conference on Web Services, 2024

   Insight

   Insight: This work proposes preliminary ideas for SLO allocation in LLM pipeline parallelism. We explore fine-grained SLO constraint mechanisms to optimize inference performance by intelligently distributing service level objectives across different pipeline stages, enabling more efficient resource utilization and better meeting diverse application requirements.

3. IEEE TCC24

   Understanding Serverless Inference in Mobile-Edge Networks: a Benchmark Approach

   Junhong Chen, Yanying Lin^*, Shijie Peng, Shuaipeng Wu, Kenneth Kent, Hao Dai, Kejiang Ye, and Yang Wang

   IEEE Transactions on Cloud Computing, 2024

2022

1. IEEE TSC22

   Serverless Computing: State-of-the-Art, Challenges and Opportunities

   Yongkang Li, Yanying Lin, Kejiang Ye, Chengzhong Xu, and Yang Wang

   IEEE Transactions on Services Computing, 2022

   Insight

   Insight: This work presents a comprehensive survey of serverless computing, providing insights into the current state-of-the-art and identifying key research challenges and future opportunities. We systematically analyze the serverless paradigm from multiple perspectives including architecture, performance, security, and application domains. The survey contributes to the community by outlining promising research directions.

2021

1. IEEE/ACM ToN21

   A Novel End-to-end Deep Learning Framework for Encrypted Traffic Identification

   Peng Lin, Kejiang Ye, Yishen Hu, Yanying Lin, and Chengzhong Xu

   IEEE/ACM Transactions on Networking, 2021