vllm-project / vllm-project/production-stack
Is the router API compatible with the OpenAI protocol?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 503
- Avg merge
- 4d 17h
- Merged PRs (30d)
- 8
Description
hi I have two questions：
1 Is the router API compatible with the OpenAI protocol?
2 What architecture and above of GPU is required for the NVIDIA Inference Transfer Library (NIXL)? If the GPU does not support NIXL transfer, what transfer method will be used by default?
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 with the router API documentation and the NVIDIA Inference Transfer Library (NIXL) documentation or configuration entry points referenced by the project. Verify whether the router follows the OpenAI protocol and document supported GPU architectures plus the fallback transfer method when NIXL is unavailable.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, infrastructure
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100