In this series of blog, I am going to recap what I learned about optimizing performance in my previous work, especially for machine learning systems. And I also want to introduce some newest techniques on accelerating LLMs.
- Introduction
- Where You Are: How To Measure and Profile A Program
- Where The Peak Is: How To Calculate The Theoretical Performance Upper Bound
- What You Can Do
- Maximize The Utility Of Hardware
- Add or Upgrade Hardware
- Less Work
- Beyond Von Neumann
- Trending Applications
- My Previous Work