chore: setup for performance benchmarking (#3096)

# What does this PR do?
1. Added a simple mock openai-compat server that serves chat/completion
2. Add a benchmark server in EKS that includes mock inference server
3. Add locust (https://locust.io/) file for load testing

## Test Plan
bash apply.sh
kubectl port-forward service/locust-web-ui 8089:8089
Go to localhost:8089 to start a load test

<img width="1392" height="334" alt="image"
src="https://github.com/user-attachments/assets/d6aa3deb-583a-42ed-889b-751262b8e91c"
/>
<img width="1362" height="881" alt="image"
src="https://github.com/user-attachments/assets/6a28b9b4-05e6-44e2-b504-07e60c12d35e"
/>

docs/source/distributions/k8s-benchmark/openai-mock-deployment.yaml

@@ -0,0 +1,52 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: openai-mock
+  labels:
+    app: openai-mock
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: openai-mock
+  template:
+    metadata:
+      labels:
+        app: openai-mock
+    spec:
+      containers:
+      - name: openai-mock
+        image: python:3.12-slim
+        ports:
+        - containerPort: ${MOCK_INFERENCE_PORT}
+        env:
+        - name: PORT
+          value: "${MOCK_INFERENCE_PORT}"
+        - name: MOCK_MODELS
+          value: "${MOCK_INFERENCE_MODEL}"
+        - name: STREAM_DELAY_SECONDS
+          value: "${STREAM_DELAY_SECONDS}"
+        command: ["sh", "-c"]
+        args:
+        - |
+          pip install flask &&
+          python /app/openai-mock-server.py --port ${MOCK_INFERENCE_PORT}
+        volumeMounts:
+        - name: openai-mock-script
+          mountPath: /app
+      volumes:
+      - name: openai-mock-script
+        configMap:
+          name: openai-mock
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: openai-mock-service
+spec:
+  selector:
+    app: openai-mock
+  ports:
+  - port: 8080
+    targetPort: 8080
+  type: ClusterIP