Publications

Zizhao Mo, Junlin Chen, Huanle Xu, Chengzhong Xu (2026). Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking. In SIGMOD 2026.

Wenyan Chen, Chengzhi Lu, Kejiang Ye, Huanle Xu, Chengzhong Xu (2026). High Throughput and Low Latency LLM Serving via Adaptive KV Caching. In Eurosys 2026.

Xiaosong Chen, Wenyan Chen, Yuanhang Chen, Huanle Xu (2026). FedSUV: Validity and Utility-guided Client Selection for Federated Learning. In INFOCOM 2026.

Yuanhang Chen, Xiaosong Chen, Wenyan Chen, Huanle Xu (2025). FedDance: Efficient Participant Selection for Federated Learning in Highly Dynamic Environments. In SoCC 2025.

Zizhao Mo, Jianxiong Liao, Huanle Xu, Zhi Zhou, Chengzhong Xu (2025). Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism. In SC 2025.

Wenyan Chen, Chengzhi Lu, Huanle Xu, Kejiang Ye, Chengzhong Xu (2025). Multiplexing Dynamic Deep Learning Workloads with SLO-awareness in GPU Clusters. In Eurosys 2025.

Liao Chen, Chenyu Lin, Shutian Luo, Huanle Xu, Chengzhong Xu (2025). Grad: Intelligent Microservice Scaling by Harnessing Resource Fungibility. In HPCA 2025.

Zizhao Mo, Huanle Xu, Wing Cheong Lau (2025). Fast and Fair Training for Deep Learning in Heterogeneous GPU Clusters. In ICS 2025.

Shutian Luo, Jianxiong Liao, Chenyu Lin, Huanle Xu, Zhi Zhou, Chengzhong Xu (2025). Embracing Imbalance: Dynamic Load Shifting among Microservice Containers in Shared Clusters. In ASPLOS 2025.

Xiaosong Chen, Hanqin Zhuang, Yang Liu, Huanle Xu, Wing Cheong Lau (2025). Combinatorial Multi-Armed Bandits with Fairness Constraints: An Online Convex Optimization Perspective. Journal of Artificial Intelligence Research, 2025.

Zizhao Mo, Huanle Xu, Wing Cheong Lau (2024). Optimal Resource Efficiency with Fairness in Heterogeneous GPU Clusters. In Middleware 2024.

Chengzhi Lu, Huanle Xu, Yudan Li, Wenyan Chen, Kejiang Ye, Chengzhong Xu (2024). SMIless: Serving DAG-based Inference with Dynamic Invocations under Serverless Computing. In SC 2024.

Liao Chen, Shutian Luo, Chenyu Lin, Zizhao Mo, Huanle Xu, Kejiang Ye, Chengzhong Xu (2024). Derm: SLA-aware Resource Management for Highly Dynamic Microservices. In ISCA 2024.

Xiaosong Chen, Huanle Xu, Chengzhong Xu (2024). Optimizing Dynamic Data Center Provisioning through Speed Scaling: A Primal-Dual Perspective. In SPAA 2024.

Zizhao Mo, Huanle Xu, Chengzhong Xu (2024). Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters. In ASPLOS 2024.

Shutian Luo, Chenyu Lin, Kejiang Ye, Guoyao Xu, Liping Zhang, Guodong Yang, Huanle Xu, Chengzhong Xu (2024). Optimizing Resource Management for Shared Microservices: A Scalable System Design. ACM Transactions on Computer Systems (ToCS), 42(1-2).

Wenyan Chen, Zizhao Mo, Huanle Xu, Kejiang Ye, Chengzhong Xu (2023). Interference-aware Multiplexing for Deep Learning in GPU Clusters A Middleware Approach. In SC 2023.

Da Sun Handason Tam, Yang Liu,, Huanle Xu, Siyue Xie, Wing Cheong Lau (2023). PERT-GNN: Latency Prediction for Microservice-based Cloud-Native Applications via Graph Neural Networks. In KDD 2023.

Chengzhi Lu, Huanle Xu, Keying Ye, Guoyao Xu, Liping Zhang, Guodong Yang, Chengzhong Xu (2023). Understanding and Optimizing Workloads for Unified Resource Management in Large Cloud Platforms. In EuroSys 2023.

Shutian Luo, Huanle Xu, Kejiang Ye, Guoyao Xu, Liping Zhang, Jian He, Guodong Yang, Chengzhong Xu (2023). Erms: Efficient Resource Management for Shared Microservices with SLA Guarantees. In ASPLOS 2023.

Yang Liu, Huanle Xu, Wing Cheong Lau (2023). Cloud Configuration Optimization for Recurring Batch-Processing Applications. IEEE Transactions on Parallel and Distributed Systems (TPDS) 34(5).

Shutian Luo, Huanle Xu, Kejiang Ye, Guoyao Xu, Liping Zhang, Guodong Yang, Chengzhong Xu (2022). The Power of Prediction Microservice Auto Scaling via Workload Learning. In ACM SoCC 2022.

Shutian Luo, Huanle Xu, Chengzhi Lu, Kejiang Ye, Guoyao Xu, Liping Zhang, Jian He, Chengzhong Xu (2022). An In-Depth Study of Microservice Call Graph and Runtime Performance. IEEE Transactions on Parallel and Distributed Systems (TPDS), 33(12).

Huanle Xu, Yang Liu, Wing Cheong Lau (2022). Multi Resource Scheduling with Task Cloning in Heterogeneous Clusters. In ICPP 2022.

Shutian Luo, Huanle Xu, Chengzhi Lu, Kejiang Ye, Guoyaao Xu, Liping Zhang, Yu Ding, Jian He, Chengzhong Xu (2021). Characterizing Microservice Dependency and Performance: Alibaba Trace Analysis. In ACM SoCC 2021 (Best Paper Award).

Huanle Xu, Yang Liu, Wing Cheong Lau (2021). Optimal Job Scheduling with Resource Packing for Heterogeneous Servers. IEEE/ACM Transactions on Networking (ToN), 29(4).