OpenAI OSS support
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 1.3k
- Avg merge
- 5h 36m
- Merged PRs (30d)
- 22
Description
OpenAI released 2 OSS models that are SOTA: 20B, 120B MoE.
https://github.com/openai/gpt-oss
SGLang already supports inference. This would be a game changer for RL training. What's slime's roadmap to supporting this?
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
Start by reviewing slime's current RL training and inference integration, then compare it with the SGLang support referenced in the issue and the gpt-oss repository. Done means defining and implementing a supported path for training with OpenAI's 20B and 120B MoE models, with the relevant validation documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100