Hello, World

This is the first post on my blog. I plan to write about GPU programming, MLOps, and the things I learn while trying to make computers go fast.

Why write?

Writing forces clarity. If I can't explain a concept in plain language, I probably don't understand it well enough. Plus, the CUDA documentation could use some human-friendly companions.

What to expect

• Deep dives into CUDA kernel optimization
• MLOps patterns and anti-patterns
• Notes on papers I'm reading
• Occasional rants about memory bandwidth

Stay tuned.