Weiming Hu
Weiming Hu (胡洧铭)
Ph.D. Student, Shanghai Jiao Tong University

Hi! I am currently a third-year Ph.D. student in the Department of Computer Science and Engineering of Shanghai Jiao Tong University, advised by Prof. Jingwen Leng.

Before this, I obtained my master degree at School of Information Science and Technology (SIST), ShanghaiTech University. I at that time researched under the supervision of Prof. Xin Lou and Dr. Yuanfeng Wang. I received the B.E. degree from College of Architecture & Environment, Sichuan University in 2020.

My research interests include Computer Architecture, with a focus on LLM Quantization, GPGPU Micro-architecture, and Hardware/Software Co-Design.

I expect to graduate in 2027 and am actively seeking industry positions in efficient LLM inference systems and AI chip architecture. Feel free to reach out.

News


  • 07/2026: Selected for the CIE-Tencent Doctoral Research Incentive Project (44 recipients nationwide).
  • 07/2026: Serving as Volunteer Chair of APPT 2026.
  • 03/2026: M2XFP received the Best Paper Honorable Mention at ASPLOS 2026.
  • 11/2025: One paper is accepted by ASPLOS 2026. Thanks to all my collaborators!
  • 09/2025: One paper is accepted by NeurIPS 2025.
  • 01/2025: Received the Student Travel Grant of HPCA 2025.
  • 12/2024: Participated in ChinaSys @ Tianjin.
  • 11/2024: One paper is accepted by HPCA 2025. Thanks to all my collaborators!
  • 09/2023: Started my Ph.D. studies at Shanghai Jiao Tong University.

Publications


Conference Papers
eLLM: Elastic Memory Management Framework for Efficient LLM Serving
Jiale Xu, Rui Zhang, Yi Xiong, Cong Guo, Zihan Liu, Yangjie Zhou, Weiming Hu, Hao Wu, Changxu Shao, Ziqing Wang, Yongjie Yuan, Junping Zhao, Minyi Guo, Jingwen Leng
The 63rd Design Automation Conference (DAC 2026)
M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization
Weiming Hu, Zihan Zhang, Haoyan Zhang, Chen Zhang, Cong Guo, Yu Feng, Tianchi Hu, Guanglin Li, Guipeng Hu, Junsong Wang, Jingwen Leng
Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2026)
Best Paper Honorable Mention
Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
Yue Guan, Changming Yu, Shihan Fang, Weiming Hu, Zaifeng Pan, Zheng Wang, Zihan Liu, Yangjie Zhou, Yufei Ding, Minyi Guo, Jingwen Leng
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type
Weiming Hu, Haoyan Zhang, Cong Guo, Yu Feng, Renyang Guan, Zhendong Hua, Zihan Liu, Yue Guan, Minyi Guo, Jingwen Leng
International Symposium on High-Performance Computer Architecture (HPCA 2025)
OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization
Cong Guo*, Jiaming Tang*, Weiming Hu, Jingwen Leng, Chen Zhang, Fan Yang, Yunxin Liu, Minyi Guo, Yuhao Zhu
Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA 2023)
Cache-locality Based Adaptive Warp Scheduling for Neural Network Acceleration on GPGPUs
Weiming Hu, Yi Zhou, Ying Quan, Yuanfeng Wang, Xin Lou
IEEE 35th International System-on-Chip Conference (SOCC 2022)
Technical Reports & Preprints
Kimi K3: Open Frontier Intelligence
Kimi Team (including Weiming Hu)
Technical Report, Moonshot AI, 2026

Honors & Awards


  • 2026: CIE-Tencent Doctoral Research Incentive Project (中国电子学会-腾讯博士生科研激励计划), 44 recipients nationwide, ¥100,000 grant.
  • 2026: Best Paper Honorable Mention, ASPLOS 2026.
  • 2025: Outstanding Intern of the Year, Shanghai Qi Zhi Institute.
  • 2025: Student Travel Grant, HPCA 2025.
  • 2019: First Prize (Sichuan Province), Chinese Mathematics Competition for College Students.

Experience


  • 2026.04 - Now, Research Intern, AI Infra Team, Moonshot AI (Kimi).
  • 2021.08 - 2022.06, Architecture R&D Intern, Glenfly Tech. GPU architecture performance analysis tooling.

Service


  • Volunteer Chair, International Symposium on Advanced Parallel Processing Technologies (APPT 2026)
  • Reviewer, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Artifact Evaluation Committee, IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS 2026)

Teaching


  • CS2911: Introduction to Computing. Summer 2024, Teaching Assistant, Shanghai Jiao Tong University
  • CS2651: Computer Architecture. Spring 2024, Teaching Assistant, Shanghai Jiao Tong University
  • CS110: Computer Architecture I. Spring 2023, Teaching Assistant, ShanghaiTech University

Education


2023.09 - Now, Ph.D. student in Computer Science, Department of Computer Science and Engineering, Shanghai Jiao Tong University. (expected graduation: 2027)
2020.09 - 2023.06, M.S. in Computer Science, School of Information Science and Technology, ShanghaiTech University.
2016.09 - 2020.06, B.E. in Civil Engineering, College of Architecture & Environment, Sichuan University.

Projects


  • M2XFP — metadata-augmented microscaling format for FP4 quantization.
  • M-ANT — mathematically adaptive numerical type for low-bit weight and KV cache compression.
  • CAWS — cache-locality based adaptive warp scheduling on GPGPUs.