ML Realization
A comprehensive implementation of various machine learning algorithms from scratch, with focus on neural networks and deep learning architectures.
Project Highlights
- Built neural network layers and activation functions from fundamental principles
- Implemented gradient descent optimization with various approaches
- Created visualization tools to understand model training and decision boundaries
- Containerized the entire environment for reproducible experiments
Technologies Used
Python, NumPy, TensorFlow, Matplotlib, Docker, Jupyter Notebooks
Yuque motivated KaTeX printing Notes
A specialized system for generating beautifully formatted academic notes using KaTeX rendering inspired by Yuque's document format. Perfect for researchers and students who need to create, share, and print complex mathematical content.
Project Highlights
- Developed a custom template system for academic papers and notes
- Created a Python-based converter to transform Yuque documents to KaTeX
- Built an automatic reference management system
- Designed print-optimized stylesheets for mathematical notation
Technologies Used
LaTeX, KaTeX, JavaScript, Python, CSS, HTML
Dynamo Project
NVIDIA Dynamo is a high-throughput low-latency inference framework designed for serving generative AI and reasoning models in multi-node distributed environments. Dynamo is designed to be inference engine agnostic (supports TRT-LLM, vLLM, SGLang or others) and captures LLM-specific capabilities.
Project Highlights
- Under construction
Technologies Used
CUDA, C++, Python, NVIDIA Libraries, Linux