AlphaUncommon
NVlabs/QeRL
[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.
- Owner
- NVlabs (organization)
- Stars
- Stars: 526
- Forks
- Forks: 52
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- llmsquantizationreasoningreinforcement-learning
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by NVlabs
All 247 repos by NVlabs- NVlabs/instant-ngpStars: 17,585CudaStable
- NVlabs/styleganStars: 14,408PythonStable
- NVlabs/stylegan2Stars: 11,183PythonStable
- NVlabs/SanaStars: 9,762PythonStable
- NVlabs/SPADEStars: 7,717PythonStable
- NVlabs/stylegan3Stars: 6,946PythonStable
Nearby in Python
All Python repos- ancoleman/ai-design-componentsStars: 526PythonAlpha
- joshavant/clawboxStars: 526PythonAlpha
- OpSafari/hypoarenaStars: 526PythonAlpha
- astrofrog/mpl-scatter-densityStars: 526PythonAlpha
- python-semver/python-semverStars: 526PythonAlpha
- amitu/importdStars: 526PythonAlpha