Inconsistencies in the docs around InferencePool

[christian-posta]

I think I'm seeing some inconsistency in the docs wrt names and spec definitions.

From this page: https://gateway-api-inference-extension.sigs.k8s.io/concepts/api-overview/#inferencepool

InferencePool represents a set of Inference-focused Pods and an extension that will be used to route to them. Within the broader Gateway API resource model, this resource is considered a "backend". In practice, that means that you'd replace a Kubernetes Service with an InferencePool. This resource has some similarities to Service (a way to select Pods and specify a port), but has some unique capabilities. With InferenceModel, you can configure a routing extension as well as inference-specific routing optimizations. For more information on this resource, refer to our InferencePool documentation or go directly to the InferencePool spec.

Specifically "With InferenceModel, you can configure a routing extension...."

This section is about InferencePool, why is it referring to InferenceModel? Seems this is a mistake and should refer to InferencePool.

Additionally, that particular part of the doc is talking about configuring a "routing extension". Checking the spec on the docs, it doesn't show how to configure that (ie, there should be an extensionRef field, but there isn't):
https://gateway-api-inference-extension.sigs.k8s.io/reference/spec/#inferencepoolspec

Let me know if these are oversights that need to be corrected, or if I am missing something.