Skip to content
View ducviet00's full-sized avatar
🥚
🥚
  • Moreh, Inc.
  • Ha Noi
  • 03:32 (UTC +07:00)
  • LinkedIn in/ducviet00

Highlights

  • Pro

Block or report ducviet00

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
ducviet00/README.md

Hi there, I'm Duc Viet 👋

Welcome to my GitHub profile! I'm passionate about Machine Learning, Deep Learning, and AI-focused projects, especially when it comes to optimizing performance, enhancing user experiences, and making data-driven decisions. Here's a quick peek into what I do and what you might find here!


👨‍💻 What I’m Working On

  • Efficient Machine Learning: Exploring performance improvements, such as quantization for large language models (LLMs) and diffusion models.
  • ML Integration & Automation: Working on optimizing model serving and training data pipelines.
  • Open-Source Projects: Actively contributing to open-source projects. Some of my past contributions include:

🔧 Technologies & Tools I Use

  • Languages: Python, C++, CUDA, ROCm
  • Libraries & Frameworks: PyTorch, Transformers, Ray, Apache Airflow
  • Tools: Kubernetes, GitLab CI, GitHub Actions, Docker
  • Platforms: AWS, GCP

📫 How to Reach Me


💬 Fun Fact

Even though I’m focused on tech, I make time to unwind, whether it’s through hiking, reading research papers, or exploring new cities whenever I get a chance. Recently, I’ve been planning a visit to a scenic destination like Nha Trang!

Thanks for stopping by! Feel free to check out my repositories, and if you’d like to collaborate or discuss a project, don’t hesitate to reach out!

Pinned Loading

  1. dotfiles dotfiles Public

    dotfiles

    Lua 10

  2. llama.cuda llama.cuda Public

    Attempting to build the fastest, minimal Llama3 inference (on my RTX 2060)

    Cuda 2