BREAKING
llm.c trains GPT in pure C/CUDA
0%
faster vs PyTorch
0%
less memory
0%
speed gain
From GPT-2 124M to GPT-3 1.6B
1GPT-2 124M
2GPT-3 miniseries
3Up to 1.6B params
Training costs at a glance
GPT-2 124Msingle node
~90 minutes
~$20
GPT-2 1.6B8x H100
~24 hours
~$600-672
Low-level, framework-free training
MIT-licensed and open on GitHub
AI NEWS BLITZ
Andrej Karpathy's llm.c pretrains GPT models in pure C and CUDA, no PyTorch needed.