diff --git a/CodeGen/README.md b/CodeGen/README.md
index 3de96461a..1eef8bac8 100644
--- a/CodeGen/README.md
+++ b/CodeGen/README.md
@@ -29,3 +29,7 @@ Refer to the [Gaudi Guide](./docker-composer/gaudi/README.md) for instructions o
 ## Deploy CodeGen on Xeon
 
 Refer to the [Xeon Guide](./docker-composer/xeon/README.md) for instructions on deploying CodeGen on Xeon.
+
+## Deploy CodeGen into Kubernetes on Xeon & Gaudi
+
+Refer to the [Kubernetes Guide](./kubernetes/manifests/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi.
diff --git a/CodeGen/kubernetes/manifests/README.md b/CodeGen/kubernetes/manifests/README.md
index e69de29bb..b7ca064e9 100644
--- a/CodeGen/kubernetes/manifests/README.md
+++ b/CodeGen/kubernetes/manifests/README.md
@@ -0,0 +1,35 @@
+<h1 align="center" id="title">Deploy CodeGen in Kubernetes Cluster</h1>
+
+> [NOTE]
+> The following values must be set before you can deploy:
+> HUGGINGFACEHUB_API_TOKEN
+> You can also customize the "MODEL_ID" and "model-volume"
+
+## Deploy On Xeon
+
+```
+cd GenAIExamples/CodeGen/kubernetes/manifests/xeon
+export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
+sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
+kubectl apply -f codegen.yaml
+```
+
+## Deploy On Gaudi
+
+```
+cd GenAIExamples/CodeGen/kubernetes/manifests/gaudi
+export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
+sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
+kubectl apply -f codegen.yaml
+```
+
+## Verify Services
+
+Make sure all the pods are running, and restart the codegen-xxxx pod if necessary.
+
+```
+kubectl get pods
+curl http://codegen:6666/v1/codegen -H "Content-Type: application/json" -d '{
+     "messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."
+     }'
+```
diff --git a/CodeGen/kubernetes/manifests/gaudi/codegen.yaml b/CodeGen/kubernetes/manifests/gaudi/codegen.yaml
new file mode 100644
index 000000000..e92c64a74
--- /dev/null
+++ b/CodeGen/kubernetes/manifests/gaudi/codegen.yaml
@@ -0,0 +1,207 @@
+---
+# Source: codegen/charts/llm-uservice/charts/tgi/templates/service.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen-tgi
+  labels:
+    helm.sh/chart: tgi-0.1.0
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 80
+      targetPort: 80
+      protocol: TCP
+      name: tgi
+  selector:
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 9000
+      targetPort: 9000
+      protocol: TCP
+      name: llm-uservice
+  selector:
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen
+  labels:
+    helm.sh/chart: codegen-0.1.0
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 6666
+      targetPort: 6666
+      protocol: TCP
+      name: codegen
+  selector:
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen-tgi
+  labels:
+    helm.sh/chart: tgi-0.1.0
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: tgi
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: tgi
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: {}
+      containers:
+        - name: tgi
+          env:
+            - name: MODEL_ID
+              value: ise-uiuc/Magicoder-S-DS-6.7B
+            - name: PORT
+              value: "80"
+          securityContext: {}
+          image: "ghcr.io/huggingface/tgi-gaudi:1.2.1"
+          imagePullPolicy: IfNotPresent
+          volumeMounts:
+            - mountPath: /data
+              name: model-volume
+          ports:
+            - name: http
+              containerPort: 80
+              protocol: TCP
+          resources:
+            limits:
+              habana.ai/gaudi: 1
+      volumes:
+        - name: model-volume
+          hostPath:
+            path: /mnt
+            type: Directory
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llm-uservice
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llm-uservice
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: {}
+      containers:
+        - name: codegen
+          env:
+            - name: TGI_LLM_ENDPOINT
+              value: "http://codegen-tgi:80"
+            - name: HUGGINGFACEHUB_API_TOKEN
+              value: "insert-your-huggingface-token-here"
+            - name: http_proxy
+              value:
+            - name: https_proxy
+              value:
+            - name: no_proxy
+              value:
+
+          securityContext: {}
+          image: "opea/llm-tgi:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: llm-uservice
+              containerPort: 9000
+              protocol: TCP
+          startupProbe:
+            exec:
+              command:
+                - curl
+                - http://codegen-tgi:80
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 120
+          resources: {}
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen
+  labels:
+    helm.sh/chart: codegen-0.1.0
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: codegen
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: codegen
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: null
+      containers:
+        - name: codegen
+          env:
+            - name: LLM_SERVICE_HOST_IP
+              value: codegen-llm-uservice
+          securityContext: null
+          image: "opea/codegen:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: codegen
+              containerPort: 6666
+              protocol: TCP
+          resources: null
diff --git a/CodeGen/kubernetes/manifests/xeon/codegen.yaml b/CodeGen/kubernetes/manifests/xeon/codegen.yaml
new file mode 100644
index 000000000..1887741cf
--- /dev/null
+++ b/CodeGen/kubernetes/manifests/xeon/codegen.yaml
@@ -0,0 +1,205 @@
+---
+# Source: codegen/charts/llm-uservice/charts/tgi/templates/service.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen-tgi
+  labels:
+    helm.sh/chart: tgi-0.1.0
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 80
+      targetPort: 80
+      protocol: TCP
+      name: tgi
+  selector:
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 9000
+      targetPort: 9000
+      protocol: TCP
+      name: llm-uservice
+  selector:
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: codegen
+  labels:
+    helm.sh/chart: codegen-0.1.0
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 6666
+      targetPort: 6666
+      protocol: TCP
+      name: codegen
+  selector:
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen-tgi
+  labels:
+    helm.sh/chart: tgi-0.1.0
+    app.kubernetes.io/name: tgi
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: tgi
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: tgi
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: {}
+      containers:
+        - name: tgi
+          env:
+            - name: MODEL_ID
+              value: ise-uiuc/Magicoder-S-DS-6.7B
+            - name: PORT
+              value: "80"
+          securityContext: {}
+          image: "ghcr.io/huggingface/text-generation-inference:1.4"
+          imagePullPolicy: IfNotPresent
+          volumeMounts:
+            - mountPath: /data
+              name: model-volume
+          ports:
+            - name: http
+              containerPort: 80
+              protocol: TCP
+          resources: {}
+      volumes:
+        - name: model-volume
+          hostPath:
+            path: /mnt
+            type: Directory
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llm-uservice
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llm-uservice
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: {}
+      containers:
+        - name: codegen
+          env:
+            - name: TGI_LLM_ENDPOINT
+              value: "http://codegen-tgi:80"
+            - name: HUGGINGFACEHUB_API_TOKEN
+              value: "insert-your-huggingface-token-here"
+            - name: http_proxy
+              value:
+            - name: https_proxy
+              value:
+            - name: no_proxy
+              value:
+
+          securityContext: {}
+          image: "opea/llm-tgi:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: llm-uservice
+              containerPort: 9000
+              protocol: TCP
+          startupProbe:
+            exec:
+              command:
+                - curl
+                - http://codegen-tgi:80
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 120
+          resources: {}
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: codegen
+  labels:
+    helm.sh/chart: codegen-0.1.0
+    app.kubernetes.io/name: codegen
+    app.kubernetes.io/instance: codegen
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: codegen
+      app.kubernetes.io/instance: codegen
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: codegen
+        app.kubernetes.io/instance: codegen
+    spec:
+      securityContext: null
+      containers:
+        - name: codegen
+          env:
+            - name: LLM_SERVICE_HOST_IP
+              value: codegen-llm-uservice
+          securityContext: null
+          image: "opea/codegen:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: codegen
+              containerPort: 6666
+              protocol: TCP
+          resources: null