llm.c (via) Andrej Karpathy implements LLM training—initially for GPT-2, other architectures to follow—in just over 1,000 lines of C on top of CUDA. Includes a tutorial about implementing LayerNorm by porting an implementation from Python.
Recent articles
- New audio models from OpenAI, but how much can we rely on them? - 20th March 2025
- Calling a wrap on my weeknotes - 20th March 2025
- Not all AI-assisted programming is vibe coding (but vibe coding rocks) - 19th March 2025