Adding terminationGracePeriodSeconds to match vLLMs

Author: kfswain

config/manifests/inferencemodel.yaml

@@ -1,7 +1,7 @@
 apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
-  name: tweet-summarizer
+  name: food-review
 spec:
   modelName: food-review
   criticality: Standard

config/manifests/inferencepool.yaml

@@ -41,6 +41,8 @@ spec:
       labels:
         app: vllm-llama3-8b-instruct-epp
     spec:
+      # Conservatively, this timeout should mirror the longest grace period of the pods within the pool
+      terminationGracePeriodSeconds: 130
       containers:
       - name: epp
         image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main