A PDF version of this résumé is available here.

No. 100, Fuxing Rd., High-Tech District, Hefei, Anhui Province, China 230031
sh.fu@outlook.com ⬦ Fr4nk1inCs

Research Interests

LLM inference optimization, System for MoE.

Research Projects

Parallelism Planning for MoE Inference with Dynamic Top-K Routing
ADSL, USTC
Core Member
Mar 2025—Aug 2025
  • An inference framework for dymamic top-k routing MoE models, which automatically plans parallelism strategies to maximize throughput on prefill-dominated workloads.
  • Paricipated in the implementation of the model profiler, adoption of dynamic top-k routing, pipeline parallelism enhancements, and the design of the parallelism planner.

Publications

Jin, Z., Fu, S., Tang, C., Bai, Y., Wang, S., Zhu, J., Fang, C., Gong, P., & Li, C. (2026). SMIDT: High-Performance Inference Framework for MoE Models with Dynamic Top-K Routing. Proceedings of the Fortieth AAAI Conference on Artificial Intelligence.

Education

University of Science and Technology of China
Hefei, Anhui
M.E. in Computer Science and Technology
Sep 2024—Present
University of Science and Technology of China
Hefei, Anhui
B.E. in Computer Science and Technology
Sep 2020—Jun 2024

Honors & Scholarships

  • Qiangwei "Yuanzhi" Scholarship (Top 3%)
    Oct 2023, USTC
  • Jianghuai & NIO Automobile Scholarship
    Jan 2023, USTC
  • Cheng Linyi Scholarship
    Jan 2022, USTC
  • Outstanding Freshman Scholarship, Grade 2
    Sep 2021, USTC

Miscellaneous

Services

  • USENIX ATC ’25 Artifact Evaluation Committee

Teaching

  • T.A. for Compiler Principles and Techniques (Instructor: Prof. Cheng Li)
    2023 Autumn, USTC

Open Source Contributions

Skills

  • Languages: Mandarin Chinese (Native), English (Fluent)
  • Programming: Python, C/C++, Lua, Shell Script
  • Frameworks: PyTorch, vLLM, SGLang