About Me

I am a third-year Ph.D. student focusing on building storage system support for ML applications.

Education

News

• Won the 2025 Tencent Hunyuan Fellowship, awarded to only ~20 CS Ph.D. students across China.

• Won the first place at the ASPLOS 2025 / EuroSys 2025 contest on LLM inference optimization.

Publication Lists

• Weaver: Efficient Multi-LLM Serving with Attention Offloading.
  
  Shiwei Gao, Qing Wang, Shaoxun Zeng, Youyou Lu, Jiwu Shu
  
  USENIX Annual Technical Conference (USENIX ATC'25), 2025
  PDF
• GPreempt: GPU Preemptive Scheduling Made General and Efficient.
  
  Ruwen Fan, Tingxu Ren, Minhui Xie, Shiwei Gao, Jiwu Shu, Youyou Lu
  
  USENIX Annual Technical Conference (USENIX ATC'25), 2025
  PDF
• Frugal: Efficient and Economic Embedding Model Training with Commodity GPUs.
  
  Minhui Xie, Shaoxun Zeng, Hao Guo, Shiwei Gao, Youyou Lu
  
  The 30th Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'25), 2025
  PDF
• Medusa: Accelerating Serverless LLM Inference with Materialization.
  
  Shaoxun Zeng, Minhui Xie, Shiwei Gao, Youmin Chen, Youyou Lu
  
  The 30th Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'25), 2025
  PDF
• Fast State Restoration in LLM Serving with HCache.
  
  Shiwei Gao, Youmin Chen, Jiwu Shu
  
  The 20th European Conference on Computer Systems (EuroSys'25), 2025
  PDF
• Fast Core Scheduling with Userspace Process Abstraction.
  
  Jiazhen Lin, Youmin Chen, Shiwei Gao, Youyou Lu
  
  The 30th ACM Symposium on Operating Systems Principles (SOSP'24), 2024
  PDF

Honors Awarded

• National Scholarship, Tsinghua University, 2025
• Hunyuan Fellowship, 2025
• Future Scholar Scholarship (Only 2 Students from the CS Department), Tsinghua University, 2023
• Outstanding Graduate, Beihang University, 2023
• Nominated for the Shen Yuan Medal (University's Highest Undergraduate Honor, Top 20 Annually), Beihang University, 2023
• National Scholarship, Beihang University, 2020