
QeRL
by NVlabs (organization)
[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU. (description from the project’s GitHub page)
Repository facts
- Stars
- 525
- Forks
- 52
- Open issues and pull requests
- 10
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- NVlabs · Organization
- Created
- Sep 22, 2025
- Last push
- Mar 30, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,483: rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
5,425 starsJupyter NotebookApache-2.0Last push Oct 2, 2026
Rank 2,479: SkyworkAI/Skywork-R1V
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
3,173 starsPythonMITLast push Jul 29, 2026
Rank 6,274: AgileRL/AgileRL
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
959 starsPythonApache-2.0Last push Oct 16, 2026
Rank 8,308: turningpoint-ai/VisualThinker-R1-Zero
Explore the Multimodal “Aha Moment” on 2B Model
623 starsPythonNo license file detectedLast push Mar 18, 2025
Rank 6,932: whitecircle/halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
825 starsPythonOther licenseLast push Oct 15, 2026
Rank 6,376: brylevkirill/notes
Learn about Machine Learning and Artificial Intelligence
934 starsNo license file detectedLast push Feb 8, 2022