JustVugg/
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
by Vincenzo Fornaro Cuda MIT licence 26 forks Created Jun 2026 View on GitHub
- Stars
- 127
- <1% of JustVugg's stars
- Rank
- #401,308
- of 847,550 repos, top 48%
Among 847,550 repos
100–160 stars: 154,448 repos, including nanoeuler
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #398,760
- Next milestone
- +30 stars to reach the top 40%
- Popular
- One of 488,858 repos with 100+ stars