From ca8b07945ac4e4c2381b30ba60e30ccf26cc1e56 Mon Sep 17 00:00:00 2001 From: salonichf5 <146118978+salonichf5@users.noreply.github.com> Date: Fri, 26 Sep 2025 13:52:31 -0500 Subject: [PATCH 1/2] update design doc to include conditions about routes and extension ref --- docs/proposals/gateway-inference-extension.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/docs/proposals/gateway-inference-extension.md b/docs/proposals/gateway-inference-extension.md index fb6abe3ae2..f9e988181e 100644 --- a/docs/proposals/gateway-inference-extension.md +++ b/docs/proposals/gateway-inference-extension.md @@ -106,6 +106,15 @@ InferenceObjective represents the desired state of a specific model use case. As It is my impression that this API is purely for the EPP to handle, and does not need to be handled by NGINX Gateway Fabric. +### Inference Status + +Each InferencePool publishes two conditions that together describe its overall state. The first is the `Accepted` condition, which communicates whether the pool is referenced by an HTTPRoute that the Gateway has accepted. When the route is not accepted, this condition is explicitly set to `False` with the reason `InferencePoolReasonHTTPRouteNotAccepted`, making it clear that the Gateway rejected the route referencing the pool. + +The second is the `ResolvedRefs` condition, which reflects whether the `EndpointPickerRef` associated with the pool is valid. If it is misconfigured such as being an unsupported kind, left undefined, or pointing to a non-existent Service, this condition is set to `False` with the reason `InferencePoolReasonInvalidExtensionRef`. + +The status of an InferencePool records the Gateway as its parent reference and associates it with the relevant conditions; when all conditions are `True`, the pool is valid and traffic can be directed to it. + + ### Personas and Processes Two new personas are introduced, the `Inference Platform Owner/Admin` and `Inference Workload Owner`. From a7b5e9b2b35e5d6272efc307beb8eae2d5ff15d8 Mon Sep 17 00:00:00 2001 From: salonichf5 <146118978+salonichf5@users.noreply.github.com> Date: Fri, 26 Sep 2025 14:18:50 -0500 Subject: [PATCH 2/2] remove extra line --- docs/proposals/gateway-inference-extension.md | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/proposals/gateway-inference-extension.md b/docs/proposals/gateway-inference-extension.md index f9e988181e..a5ba30722f 100644 --- a/docs/proposals/gateway-inference-extension.md +++ b/docs/proposals/gateway-inference-extension.md @@ -114,7 +114,6 @@ The second is the `ResolvedRefs` condition, which reflects whether the `Endpoint The status of an InferencePool records the Gateway as its parent reference and associates it with the relevant conditions; when all conditions are `True`, the pool is valid and traffic can be directed to it. - ### Personas and Processes Two new personas are introduced, the `Inference Platform Owner/Admin` and `Inference Workload Owner`.