abhisheknair10/Llama3.cu
Lightweight Llama 3 8B Inference Engine in CUDA C
12 best points · 0 comments · 1 Hacker News post · 52 GitHub stars · View on GitHub
Hacker News discussions
- Show HN: Lightweight Llama3 Inference Engine – CUDA C (12 points, 0 comments, by abhisheknair10, 2025-01-04)