Skip to content
View YoctoHan's full-sized avatar
🐢
hard working
🐢
hard working
5 followers · 5 following
  • Beijing
  • 10:53 (UTC +08:00)

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report YoctoHan

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
YoctoHan/README.md

Hi there, I'm YoctoHan


 About me

Unicorn

I am a Mathematics graduate with a Master's degree, currently working on deep learning infrastructure development. I am expanding my expertise in deep learning, large language models, training/inference frameworks, and high-performance computing. I have experience in building foundational systems for AI/ML applications, and my goal is to deepen my technical skills in performance and system optimization. I love to explore innovative solutions and tackle challenging technical problems.

  • 📚 I'm currently learning ...

    • LLM Inference Optimization
    • CUDA Programming
    • Algorithm

  • 🚀 I'm eager to contribute to groundbreaking AI infrastructure projects.

  • ✔ Feel free to ask me anything! I'm passionate about sharing knowledge in deep learning and HPC. Outside tech, I enjoy 🥾 hiking in nature, 🎸 listening to rock music, 🏕️ camping under the stars, and I also love playing 🃏 Texas Hold'em poker with friends.

  • 📫 Reach out to me at: [email protected]

  Skills

Languages & Syntax:

C++  Python  nVIDIA  LaTeX 

ML & DL

PyTorch  PaddlePaddle 

LLM Inference

vLLM  LMDeploy  SGLang  TensorRT-LLM 

Deployment & Cloud Services:

Docker 

 Github Stats

YoctoHan streak



visitors counter


Pinned Loading

  1. Yocto-AlgoGym Yocto-AlgoGym Public

    Yocto-AlgoGym is a self-developed algorithm training project designed to systematically enhance algorithm design and problem-solving skills. The project integrates a testing framework that supports…

    C++ 2

  2. Yocto-Infra Yocto-Infra Public

    This repository serves as a comprehensive collection of research, implementations, and benchmarks focused on Large Language Model (LLM) infrastructure technologies. It documents my ongoing explorat…

    Cuda 1

  3. opencompass opencompass Public

    Forked from open-compass/opencompass

    OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

    Python 1