About asynchronous generation and training like AReal
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.8k
- Forks
- 989
- Avg merge
- 6h 29m
- Merged PRs (30d)
- 85
Description
One question about ART framework, will we plan to support asynchronous generation/rollout and training, like https://github.com/inclusionAI/AReaL?tab=readme-ov-file (paper: https://arxiv.org/pdf/2505.24298)?
Essentially, it is a non-blocking rollout mechanism so that the ready-to-use rollout group can be sent to training queue, instead of waiting (If I understand correctly)
Best Regards
Orlando
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No ART files, tests, or entry points are named. Start by reading the linked AReaL README and paper, then map their non-blocking rollout and training queue model onto ART; done would require a decided scope and documented implementation plan for asynchronous generation and training.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100