- Category
- AI Tools
- Pricing
- Open Source
- Type
- TOOL
- Builder
- karpathy
- GitHub
- 30.6k stars
- Added
- May 22, 2026
About
Andrej Karpathy's LLM training implementation in pure C/CUDA — small, readable, performant reference for understanding GPT training from the metal up.
Why it made the leaderboard
Andrej Karpathy's LLM training implementation in pure C/CUDA — small, readable, and performant enough to actually understand GPT training from the metal up, without framework layers in the way.
Tags
llmtrainingccudakarpathy
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.