Live Projects
A real-time queue of what I'm currently working on.
Created: Jun 28, 2026 Modified: Jun 28, 2026
Project Overview
- What I’m building: I am building a system to reduce the memory footprint and improve the inference speed of large language models.
- Why I’m building it: I need to deploy large models more efficiently on limited hardware.
- Why it matters: This makes powerful LLMs more accessible and practical for real-world applications.
Current Progress & Methods
- I have just started the project.
- I am setting up my development environment and project structure.