NVlabs/
[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.
by NVIDIA Research Projects Python Apache-2.0 licence 52 forks Created Sept 2025 View on GitHub
- Stars
- 527
- <1% of NVlabs's stars
- Rank
- #120,175
- of 852,204 repos, top 15%
- In Python
- #22,394
- of 173,304 repos, top 13%
Among 852,204 repos
400–630 stars: 51,566 repos, including qerl
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 #119,941
- Next milestone
- +240 stars to reach the top 10%
- Popular
- One of 490,852 repos with 100+ stars
- Yearly average
- 462 stars a year since Sept 2025