Skip to content
View jhinpan's full-sized avatar
🫠
Hungry
🫠
Hungry
64 followers · 100 following
  • Madison
  • 04:40 (UTC -05:00)

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: Starstruckx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex4Achievement: Pull Sharkx3Achievement: Starstruckx2Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Organizations

@RLsys-Foundation

Block or report jhinpan

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jhinpan/README.md

Hi there, I'm Jin Pan(潘劲 in Chinese)! 👋

I just graduated from the traditional M.S./Ph.D. program in Computer Sciences at the University of Wisconsin–Madison. Alongside my studies, I actively contribute to the SGLang community and slime, focusing on enhancing Agentic RL Sys. My academic background includes undergraduate degrees in Computer Science Engineering from the University of Michigan, where I engaged with the Human-Centered Computing Laboratory, and in Electrical and Computer Engineering from Shanghai Jiao Tong University.

Research Interests 🔭

My research primarily focuses on:

  • RL Training & Inference: Topics related to SGLang, slime, and miles.
  • Agentic System: Topics related to Long-Horizon Coding Agent and RLHF for Multi-Agent Systems.
  • Extended Reality: Topics related to Virtual Reality and Augmented Reality.

Updates 😄

  • I'm excited to share that I will be joining the AMD Co-Design Team starting June 2026, focusing on agentic kernel code optimization!

Contact 📫

Feel free to reach out via:

Pinned Loading

  1. RLsys-Foundation/TritonForge RLsys-Foundation/TritonForge Public

    🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation feedback, cross-platform NVIDIA/AMD, Kernelbook + KernelBench

    Python 142 6

  2. RLsys-Foundation/APRIL RLsys-Foundation/APRIL Public

    APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM training.

    Python 60 4

  3. sgl-project/sglang sgl-project/sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python 29.9k 6.9k

  4. THUDM/slime THUDM/slime Public

    slime is an LLM post-training framework for RL Scaling.

    Python 7.3k 1k

  5. jhinpan.github.io jhinpan.github.io Public

    Jhinpan's porfolio based on al-folio

    HTML

  6. zhaochenyang20/Awesome-ML-SYS-Tutorial zhaochenyang20/Awesome-ML-SYS-Tutorial Public

    My learning notes for ML SYS.

    Python 6.7k 455