Skip to content
View yingxudeng's full-sized avatar
🎯
Focusing
🎯
Focusing
4 followers · 0 following
  • JD.com https://github.com/xLLM-AI
  • Beijing, China

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: Quickdraw

Block or report yingxudeng

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
yingxudeng/README.md

Hi, I'm Yingxu Deng 👋

LLM Inference Engineer at JD.com · Building fast, efficient, production-grade inference for large language models.

xLLM core contributor Production at JD.com C++ Python

About the project

jd-opensource/xllm — A high-performance LLM inference engine optimized for diverse AI accelerators (NPU, CUDA). Deployed in JD.com's core retail businesses: customer service, risk control, supply chain, and ad recommendation.

Featured project

jd-opensource/xllm

📫 yingxudeng@gmail.com

Pinned Loading

  1. xLLM-AI/xllm xLLM-AI/xllm Public

    A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

    C++ 1.5k 256