| 2026 | EuroSys | High Throughput and Low Latency LLM Serving via Adaptive KV Caching. | Wenyan Chen, Chengzhi Lu, Huanle Xu, Kejiang Ye, ChengZhong Xu |
| 2026 | EuroSys | FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters. | Yanying Lin, Shijie Peng, Chengzhi Lu, ChengZhong Xu, Kejiang Ye |
| 2025 | EuroSys | Multiplexing Dynamic Deep Learning Workloads with SLO-awareness in GPU Clusters. | Wenyan Chen, Chengzhi Lu, Huanle Xu, Kejiang Ye, Chengzhong Xu |
| 2024 | ICWS | Planck: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint. | Yanying Lin, Shijie Peng, Shuaipeng Wu, Yanbo Li, Chengzhi Lu, Chengzhong Xu, Kejiang Ye |
| 2024 | SC | SMIless: Serving DAG-based Inference with Dynamic Invocations under Serverless Computing. | Chengzhi Lu, Huanle Xu, Yudan Li, Wenyan Chen, Kejiang Ye, Chengzhong Xu |
| 2023 | EuroSys | Understanding and Optimizing Workloads for Unified Resource Management in Large Cloud Platforms. | Chengzhi Lu, Huanle Xu, Kejiang Ye, Guoyao Xu, Liping Zhang, Guodong Yang, Chengzhong Xu |
| 2021 | CLOUD | Characterizing Microservice Dependency and Performance: Alibaba Trace Analysis. | Shutian Luo, Huanle Xu, Chengzhi Lu, Kejiang Ye, Guoyao Xu, Liping Zhang, Yu Ding, Jian He, Chengzhong Xu |
| 2021 | CLUSTER | RPTCN: Resource Prediction for High-dynamic Workloads in Clouds based on Deep Learning. | Wenyan Chen, Chengzhi Lu, Kejiang Ye, Yang Wang, Cheng-Zhong Xu |
| 2019 | ICPADS | ADGS: Anomaly Detection and Localization Based on Graph Similarity in Container-Based Clouds. | Chengzhi Lu, Kejiang Ye, Wenyan Chen, Cheng-Zhong Xu |
| 2018 | ICPADS | Modeling Application Performance in Docker Containers Using Machine Learning Techniques. | Kejiang Ye, Yanmin Kou, Chengzhi Lu, Yang Wang, Cheng-Zhong Xu |