Hi, there! Welcome to my GitHub profile! I am a Doctoral Student in Computer Science at Oregon State University with a strong interest in LLM serving, AI for Science, and Efficient AI. I am closely working with vLLM and building some features on top of vLLM. I am open to opportunities that can work with the LLM inference and training system. Let's connect!
- 05/2026: Our paper "FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving" is selected as the best paper candidate.
- 04/2026: I received the OSU Graduate Student Scholarly Presentation Award 🎉.
- 04/2026: One co-author paper "Evaluating LLM Coding Agents on SZ-Family Lossy Compression Across Architectures" is accepted in IPDPS 2026 HPAI4S.
- 02/2026: Our paper "FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving" is accepted in ACM International Conference on Supercomputing (ICS'26).
- 12/2025: Our paper "LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation" is accepted in IPDPS'26.
- 09/2025: I will work as an intern at Oak Ridge National Laboratory. My work focuses mainly on large-scale LLM deployment on a GPU cluster.
- 03/2025: I had a paper presentation on conference of AAAI 2025 symposium on GenAI@Edge.
- 02/2025: Our paper "HurriCast: Synthetic Tropical Cyclone Track Generation for Hurricane Forecasting" is accepted to the SSS-25 symposium at AAAI 2025.
-
Doctorate in Computer Science Oregon State University (08/2023–Now) Research Interest: LLM serving, Efficient AI, AI for Science, and Explainable AI.
-
Master of Engineering in Electronic Information
University of Electronic Science and Technology of China (09/2020–06/2023) -
Bachelor of Science in Energy and Power Engineering
Xi Hua University (09/2014–06/2018)
- OSU Graduate Student Scholarly Presentation Award, Oregon State University (2026)
- Best Paper Candidate, ACM International Conference on Supercomputing (ICS 2026)
- Second Prize (7th/611), 2022 Huawei Software Elite Challenge
- 2022 Huawei Embedded Software Contest — 8th/48
- 2022 ZTE Software Elite Challenge — Image Denoising Algorithm Contest
- Programming Languages: Python, C/C++, MATLAB.
- Tools: Pytorch, vLLM, SGLang, Tensorflow, Nsight system, Nsight compute, cuda programming, etc.
- CS 475/575(2026 Spring): INTRO TO PARALLEL PROGRAMMING
- CSC 599: Advanced Topics in Deep Learning & High-performance Computing
- CSC 381: Programming Languages
- Automation Equipment Maintenance Engineer
Sichuan Datang International Ganzi Hydropower Development Co., Ltd. (07/2018–08/2019)
📫 Contact:
- Email: gaosho@oregonstate.edu
Thank you for visiting my profile! Feel free to explore my repositories and collaborate on exciting projects.