vllm-project / vllm-project/production-stack
Question - pinning GPUs
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 503
- Avg merge
- 4d 17h
- Merged PRs (30d)
- 8
Description
Is there a way to pin specific GPU numbers to a vllm pod rather than specifying the amount required?
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
The issue asks whether specific GPU numbers can be pinned to a vLLM pod instead of requesting a count. Start by examining the Kubernetes GPU configuration used by the production stack and how vLLM pods receive GPU resources. Done would require a clear supported approach, or a documented explanation that this is not available.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes
- Domain
- infrastructure
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100