[vllm] Explore deprecation of local vLLM model
Open
@yfw is already working on this.
Since Sep 17, 2026.
area:model
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 324
Description
Local vLLM model support gym owning GPU resources on the ray cluster. We should explore deprecating this path in support of users having vLLM deployed fully on an external endpoint, with gym owning the client. This would enable unbundling the vllm dependency for the model, avoiding collisions with training frameworks that may have their own vLLM version pinned
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.
Assessment
This issue has not been assessed yet.