Skip to content

Support multiple backend refs when ref is an InferencePool #4192

@salonichf5

Description

@salonichf5

Is your enhancement request related to a problem? Please describe.
Yes, we have new conformance tests GatewayWeightedAcrossTwoInferencePools that fails in the pipeline since we do not allow multiple backend refs when Inference Pool is the backend type.

What would you like to be added:
Support multiple backend refs for Inference Pools

Why this is needed:
To be gateway API inference extension conformant

Additional context
Add any other context or screenshots about the enhancement request here.

Metadata

Metadata

Assignees

Labels

enhancementNew feature or requestrefinedRequirements are refined and the issue is ready to be implemented.size/mediumEstimated to be completed within a week

Projects

Status

🏗 In Progress

Milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions