tairov/llama2.mojo
Inference Llama 2 in one file of pure 🔥
4 best points · 1 comments · 4 Hacker News posts · 2,128 GitHub stars · View on GitHub
Hacker News discussions
- Llama2 in Mojo is 15-20% faster than llama2.c (4 points, 0 comments, by yoquan, 2023-09-12)
- Llama2 Inference in pure Mojo (2 points, 0 comments, by atairov, 2023-09-11)
- Tairov/llama2.mojo: Inference Llama 2 in one file of pure (2 points, 0 comments, by freediver, 2023-09-12)
- Llama2.mojo - outperforms Karpathy’s llama2.c by 30% in multi-threaded inference (2 points, 1 comments, by swyx, 2023-12-04)