Skip to content
View genggng's full-sized avatar
🏠
Working from home
🏠
Working from home
15 followers · 22 following

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report genggng

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
genggng/README.md

Hi there 👋

Hi, I am Shigeng Wang (王世耿). My research sits at the intersection of LLM efficiency and real-world deployment — working on quantization, compression, and hardware-aware inference to make foundation models faster and cheaper.

🧠 Researcher @ Intel Labs China
🎓 PhD Candidate @ BUPT, Expected June 2026
📍 Beijing, China

GitHub Stats

Gmail Google Scholar ORCID 个人主页

🎯 Research & Tech Stack

Research Directions

  • LLM Quantization & Compression — Post-training quantization, low-bit precision, layer-wise sensitivity analysis
  • Efficient Inference — KVcache optimization, kernel fusion, hardware-aware deployment

Languages & Frameworks
Python, PyTorch, CUDA, C/C++

ML/AI Tools
vLLM, LLama.cpp (GGUF), OpenVINO, FlashAttention, PagedAttention

🎓 Education

  • 2021.09 – 2026.06, Ph.D. in Computer Science, Beijing University of Posts and Telecommunications
  • 2017.09 – 2021.06, B.Eng. in Data Science and Big Data Technology, Beijing University of Posts and Telecommunications

💼 Work Experience

  • 2024.04 – now, Research Intern, Intel Labs China, Supervised by Anbang Yao
  • 2023.10 – 2024.03, Research Intern, QCraft, Focusing on autonomous driving perception

📬 Contact

📧 [email protected]
🔗 Learn more on my personal website: genggng.github.io

Pinned Loading

  1. SliderQuant SliderQuant Public

    Forked from deep-optimization/SliderQuant

    The official project website of "SliderQuant: Accurate Post-Training Quantization for LLMs" (accepted to ICLR 2026).

    Python

  2. hermes-arxiv-agent hermes-arxiv-agent Public

    一个基于 Hermes 的 agent skill：每天自动从 arXiv 抓取论文，用 AI 生成中文摘要和作者单位，推送到飞书，并提供本地静态阅读网站。

    Python 53 22

  3. overleaf-git-sync overleaf-git-sync Public

    Map an online Overleaf project to a local Git-backed working repository.

    Python 1

  4. ppq_tools ppq_tools Public

    Forked from OpenPPL/ppq_tools

    A collection of utilities for ppq， Including demo, benchmark, deployment tutorial。

    Python