Adding terminationGracePeriodSeconds to match vLLMs

Author: kfswain

config/manifests/inferencepool-resources.yaml

@@ -42,6 +42,8 @@ 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