MicroGPT-C

What it can do

• Train a transformer language model from scratch

  Text training data → Trained GPT model weights

• Generate text samples using trained model

  Text prompt and trained model → Generated text continuation

• Compile C code with AVX2 optimizations

  Source code and compilation flags → Optimized executable binary

• Run inference on transformer model

  Model weights and input tokens → Predicted next tokens

• Execute zero-dependency C implementation

  Compiled binary → Standalone model training or inference

Why it made the leaderboard

A GPT in pure C with zero dependencies — training and inference in a codebase small enough to actually read, with AVX2 optimizations (the author reports 2.6M tokens/sec). A way to understand transformers at the memory-layout level, with no framework in the way.

Comments (0)

No comments yet