vllm-project / vllm-project/production-stack
feature: support for Kubernetes Gateway Inference Extensions
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 503
- Avg merge
- 4d 17h
- Merged PRs (30d)
- 8
Description
Describe the feature
See https://github.com/kubernetes-sigs/gateway-api-inference-extension.
These Inference Extensions are being formally specified as part of the Kubernetes Gateway API and will provide a standard interface for inference optimized load balancing algorithms such as the production stack Router.
Why do you need this feature?
Provides a (soon-to-be) standardized integration with Kubernetes Gateways.
Additional context
No response
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 reading the Kubernetes Gateway API Inference Extension specification linked in the issue and the production-stack repository's existing Kubernetes integration points. Determine the required integration scope and acceptance criteria for supporting standardized inference-optimized load balancing through Kubernetes Gateways.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes
- Domain
- infrastructure, networking
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100