Lingyun Yang | TRE @ Alibaba Group

About Me

I am currently a senior engineer in the TRE (Tech Infra and Reliability Engineering) team at Alibaba Group, working on AI infrastructure. I am also a joint postdoctoral researcher with Alibaba DAMO Academy and Shanghai Jiao Tong University (SJTU). Before that, I received my Ph.D. degree in Department of Computer Science and Engineering from Hong Kong University of Science and Technology (HKUST) and my B.Eng. degree in School of Computer Science and Engineering from South China University of Technology (SCUT).

My research interests center on how agents can re-architect the entire AI infrastructure stack. I am particularly interested in building agentic systems that improve GPU efficiency across the stack, from kernel agents and engine optimization to resource scheduling and orchestration.

I am open to potential collaborations. Please feel free to contact me if you are interested in my research.

Education

Ph.D., Computer Science and Engineering, Hong Kong University of Science and Technology, 2020 – 2025
B.Eng., Computer Science and Engineering, South China University of Technology, 2016 – 2020

Professional Experience

Senior Engineer, Alibaba Group, Dec. 2025 – Present (via AliStar Top Talent Program)

Internship

Research Intern, Alibaba Group, Dec. 2020 – Dec. 2025
Research Intern, Microsoft Research Asia (MSRA), Jul. 2019 – Jun. 2020

Selected Publications [View All]

^* Equal contribution ^# Student advised by me

ATC

Model-as-a-Service in the Wild: Characterizing Production LLM Inference Clusters at Scale

Yiyun Zheng^#, Lingyun Yang, Yinghao Yu, Guodong Yang, Liping Zhang, Minchen Yu

ACM SIGOPS Annual Technical Conference (ATC), 2026.

arXiv

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

Lingyun Yang*, Yuxiao Wang*, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao Yu, Guodong Yang, Liping Zhang

arXiv preprint arXiv:2607.14541, 2026.

PDF arXiv Atrex-Bench Atrex-Kernel-Agent

SOSP

DiFlow: A System for Micro-Serving Text-to-Image Diffusion Workflows

Lingyun Yang*, Suyi Li*, Tianyu Feng, Xiaoxiao Jiang, Zhipeng Di, Weiyi Lu, Kan Liu, Yinghao Yu, Tao Lan, Guodong Yang, Lin Qu, Liping Zhang, Wei Wang

ACM Symposium on Operating Systems Principles (SOSP), 2026.

PDF Code arXiv BibTeX

OSDI

Heterogeneity at Hyperscale: Characterization and Scheduling of Large Production AI Clusters at Alibaba (Operational Systems)

Suyi Li*, Lingyun Yang*, Haoxuan Yu, Sheng Yao, Tianyuan Wu, Xiaoxiao Jiang, Hanfeng Lu, Kangjin Wang, Chenhao Wang, Shenglin Xu, Lun Wang, Qingyang Duan, Shenghao Liang, Xiu Lin, Meng Zhang, Wenchao Wu, Yinghao Yu, Guodong Yang, Liping Zhang, Wei Wang

USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2026.

PDF Slides Trace BibTeX

ATC

Katz: Efficient Workflow Serving for Diffusion Models with Many Adapters

Suyi Li*, Lingyun Yang*, Xiaoxiao Jiang, Hanfeng Lu, Dakai An, Zhipeng Di, Weiyi Lu, Jiawei Chen, Kan Liu, Yinghao Yu, Tao Lan, Guodong Yang, Lin Qu, Liping Zhang, Wei Wang

USENIX Annual Technical Conference (ATC), 2025.

PDF Code Slides arXiv Trace BibTeX

NSDI

GPU-Disaggregated Serving for Deep Learning Recommendation Models at Scale

Lingyun Yang, Yongchen Wang, Yinghao Yu, Qizhen Weng, Jianbo Dong, Kan Liu, Chi Zhang, Yanyi Zi, Hao Li, Zechao Zhang, Nan Wang, Yu Dong, Menglei Zheng, Lanlan Xi, Xiaowei Lu, Liang Ye, Guodong Yang, Binzhang Fu, Tao Lan, Liping Zhang, Lin Qu, Wei Wang

USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2025.

PDF Slides Trace BibTeX

ATC

Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation Gradient Descent

Qizhen Weng*, Lingyun Yang*, Yinghao Yu, Wei Wang, Xiaochuan Tang, Guodong Yang, Liping Zhang

USENIX Annual Technical Conference (ATC), 2023.

PDF Poster Code Slides Trace BibTeX

Selected Honors

Postgraduate Scholarship, HKUST, 2020 – 2024
Star of Tomorrow Internship Award of Excellence, MSRA, 2020
National Scholarship, China, 2019
The First Prize Scholarship, SCUT, 2017

Academic Services

Journal Reviewer: ACM Transactions on Architecture and Code Optimization (2026)
Artifact Evaluation Committee: ACM SOSP (2023, 2025), ACM SIGCOMM (2024), IEEE HPCA (2024), USENIX OSDI (2023), USENIX ATC (2023), MLSys (2023)
External Conference Reviewer: IEEE INFOCOM (2022 – 2025), IEEE ICDCS (2023, 2025), IEEE ICNP (2024), ACM APSys (2021), IEEE MSN (2021), EAI Qshine (2020)
External Journal Reviewer: IEEE Transactions on Cloud Computing (2025)
Student Volunteer: ACM APNet (2023), IEEE ICMLC & ICWAPR (2018)

Teaching Assistant

CSIT6000O: Advanced Cloud Computing (Spring 2022, Spring 2023)
COMP4651: Cloud Computing and Big Data Systems (Spring 2021, Fall 2021, Spring 2024)
COMP3511: Operating Systems (Fall 2023)

Others

I’m actively maintaining a personal website about my paper reading notes (including machine learning, systems, and other interesting stuffs) and a personal blog (in Chinese).