Skip to content
View xtst's full-sized avatar
18 followers · 7 following

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Highlights

  • Pro

Block or report xtst

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
xtst/README.md

Hi, I'm Tong Xin 👋

I am a PhD student at the Institute of Parallel and Distributed Systems (IPADS), Shanghai Jiao Tong University, advised by Prof. Haibo Chen and Prof. Mingkai Dong.

My research interests are in ML systems, AI infrastructure, and operating systems. Recently, I have been working on system support for on-device LLM inference and agentic systems.

I am also a core contributor to PowerServe, a high-performance LLM inference framework for mobile devices.

🌐 Homepage / Google Scholar / X / Xiaohongshu / Zhihu / Email

News

  • 🎉 Apr 2026: Our paper Inference in the Shadows: Taming Memory Bandwidth Contention in Mobile LLM Inference with Sereno has been accepted to OSDI 2026.
  • 🎉 Aug 2025: Our paper SwitchFS: Asynchronous Metadata Updates for Distributed Filesystems with In-Network Coordination has been accepted to EuroSys 2026.

Pinned Loading

  1. powerserve-project/PowerServe powerserve-project/PowerServe Public

    High-speed and easy-use LLM serving framework for local deployment

    C++ 155 21