NVIDIA/
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better...
by NVIDIA Corporation Python Apache-2.0 licence 895 forks Created Sept 2022 View on GitHub
- Stars
- 3,602
- 1% of NVIDIA's stars
- Rank
- #18,541
- of 847,086 repos, top 3%
- In Python
- #3,315
- of 172,210 repos, top 2%
Among 847,086 repos
2.5k–4k stars: 10,603 repos, including TransformerEngine
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 #18,540
- Next milestone
- +3,631 stars to reach the top 1%
- Popular
- One of 66,308 repos with 1k+ stars
- Yearly average
- 870 stars a year since Sept 2022