PrimeIntellect-ai/prime-rl
Agentic RL Training at Scale
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
3 releases in the last 90 days, the latest 17 days ago, with 81 contributors on GitHub.
Use Cases & Benefits
- Provides a scalable asynchronous reinforcement learning framework optimized for training large models on 1000+ GPUs.
- Enables high-throughput agentic RL training with advanced parallelism and integration for multimodal and MoE models.
- Use for developing and training large-scale RL models on multi-node GPU clusters with Slurm or Kubernetes.
- Use for experimenting with multi-turn and tool-augmented RL training on smaller GPU setups for research and prototyping.
- Use for deploying and evaluating state-of-the-art multimodal vision-language models and agentic environments with native environment integration.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
PRIME-RL: Async RL Training at Scale
The trainer works with both Hugging Face and Prime custom
ModelForCausalLMout of the box. For selected families (especially large MoE) we also ship highly optimized training code undersrc/prime_rl/trainer/models/, including expert parallelism (EP) for MoE layers and context parallelism (CP) for long sequences (see the table), and additional kernels like quack-kernels.With
[model] impl = "auto"(the default), the trainer selects that custom stack when the Hugging Face config type is registered.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+353 stars over 84 days across 8 snapshot days; best day +7 on Aug 15.
Forks
484+98
Open issues
202+6
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| photoprism/photoprism | 40.4K | — | 65 | 1 day ago |
| huggingface/diffusers | 34.8K | — | 65 | 3 days ago |
| onnx/onnx | 21.6K | — | 63 | 31 days ago |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| milesial/Pytorch-UNet | 11.7K | — | 18 | — |
| PrimeIntellect-ai/prime-rl | 2.2K | — | 54 | 17 days ago |
| Category median | 21.6K | — | 63 | — |
Also by PrimeIntellect-ai
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description