Skip to content
View DandinPower's full-sized avatar
28 followers · 34 following
  • Yang Ming Chiao Tung University
  • Hsinchu
  • 07:11 (UTC +08:00)
  • LinkedIn in/yongchengliaw

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Highlights

  • Pro

Block or report DandinPower

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
DandinPower/README.md

👋 Hi, I'm Liaw Yong-Cheng

I am currently pursuing a Master’s degree in Artificial Intelligence Innovation at National Yang Ming Chiao Tung University. With multiple honors and scholarships, I aim to further my academic journey with a PhD in Computer Science, contributing to advancements in the ML/AI systems field.

📄 Learn more about my achievements and experiences on (LinkedIn).

🧑‍💻 Open Source Contributions

Liger Kernel

Efficient Triton Kernels for LLM Training that significantly reduce GPU memory usage and improve performance.

  • Addressed the dtype mismatch in AMP training scenarios and resolved uncovered scenarios in test cases for the core functionality of the Liger Kernel (Fused Linear Cross Entropy). (#501)
  • Designed and performed a deep analysis of the advantages and disadvantages of different solutions to fix the dtype mismatch problem (#502), ensuring optimal performance in terms of memory usage and latency.

GPT Researcher

A Multi-Agent LLM workflow designed to leverage diverse source documents and LLMs to create comprehensive research reports.

  • Address the issue of redundancy in the researched report (#548).
  • Designed a workflow (#713) for temporary data storage and retrieval to enhance drafting new sections.
  • Improved the overall quality of generated reports.

🛠 Skills and Tools

Python Huggingface PyTorch TensorFlow C++ C Node.js JavaScript MySQL Redis GitHub Git Docker Visual Studio Code Linux

⚡️ My GitHub Stats

Pinned Loading

  1. Long-Context-LLM-Finetuning-Study Long-Context-LLM-Finetuning-Study Public

    This repository is for studying how to efficiently fine-tune long-context LLMs (e.g., Llama 3.1 8B for a 128K context length) on commodity machines (e.g., 8x V100).

    Python 1

  2. Liger-Kernel-Study-and-Demo Liger-Kernel-Study-and-Demo Public

    This repository contains code, experiments, and a report for a study on the Liger Kernel and its application in memory-efficient training of Large Language Models (LLMs). The report analyzes the Li…

    Python 3

  3. Liger-Kernel Liger-Kernel Public

    Forked from linkedin/Liger-Kernel

    Efficient Triton Kernels for LLM Training

    Python

  4. gpt-researcher gpt-researcher Public

    Forked from assafelovic/gpt-researcher

    GPT based autonomous agent that does online comprehensive research on any given topic

    Python

  5. Comprehensive-Vocab-CLI Comprehensive-Vocab-CLI Public

    Comprehensive-Vocab-CLI is a command-line tool designed to help you learn and remember new words and their meanings. You can input a word, and the tool will provide you with the meaning of the word…

    Python