zhihu/
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
by Zhihu C++ MIT licence 84 forks Created Mar 2019 View on GitHub
- Stars
- 546
- 3% of zhihu's stars
- Rank
- #115,968
- of 847,188 repos, top 14%
- In C++
- #6,116
- of 45,203 repos, top 14%
Among 847,188 repos
400–630 stars: 51,400 repos, including cuBERT
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 #115,768
- Next milestone
- +223 stars to reach the top 10%
- Popular
- One of 488,466 repos with 100+ stars
- Yearly average
- 71 stars a year since Mar 2019