diff --git a/CodeGen/kubernetes/helm/README.md b/CodeGen/kubernetes/helm/README.md
index d496fbe51b..e67341126e 100644
--- a/CodeGen/kubernetes/helm/README.md
+++ b/CodeGen/kubernetes/helm/README.md
@@ -131,3 +131,150 @@ Optionally, delete the namespace if it's no longer needed and empty:
 ```bash
 # kubectl delete ns codegen
 ```
+
+## Deploy on AMD ROCm using Helm charts from the binary Helm repository
+
+```bash
+mkdir ~/codegen-k8s-install && cd ~/codegen-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/CodeGen/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="Qwen/Qwen2.5-Coder-7B-Instruct"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/codegen-k8s-install/GenAIExamples/CodeGen/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/codegen-k8s-install/GenAIExamples/CodeGen/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+helm upgrade --install codegen oci://ghcr.io/opea-project/charts/codegen \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+helm upgrade --install codegen oci://ghcr.io/opea-project/charts/codegen \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-tgi-values.yaml
+```
+
+## Deploy on AMD ROCm using Helm charts from Git repositories
+
+### Creating working dirs
+
+```bash
+mkdir ~/codegen-k8s-install && cd ~/codegen-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+git clone https://github.com/opea-project/GenAIInfra.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/CodeGen/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="Qwen/Qwen2.5-Coder-7B-Instruct"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/codegen-k8s-install/GenAIExamples/CodeGen/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/codegen-k8s-install/GenAIExamples/CodeGen/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+cd ~/codegen-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update codegen
+helm upgrade --install codegen codegen \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/CodeGen/kubernetes/helm/rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+cd ~/codegen-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update codegen
+helm upgrade --install codegen codegen \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/CodeGen/kubernetes/helm/rocm-tgi-values.yaml
+```
diff --git a/CodeGen/kubernetes/helm/rocm-tgi-values.yaml b/CodeGen/kubernetes/helm/rocm-tgi-values.yaml
new file mode 100644
index 0000000000..40b81a9bd9
--- /dev/null
+++ b/CodeGen/kubernetes/helm/rocm-tgi-values.yaml
@@ -0,0 +1,45 @@
+# Copyright (c) 2025 Advanced Micro Devices, Inc.
+
+
+tgi:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: ghcr.io/huggingface/text-generation-inference
+    tag: "2.4.1-rocm"
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"
+  MAX_INPUT_LENGTH: "1024"
+  MAX_TOTAL_TOKENS: "2048"
+  USE_FLASH_ATTENTION: "false"
+  FLASH_ATTENTION_RECOMPUTE: "false"
+  HIP_VISIBLE_DEVICES: "0"
+  MAX_BATCH_SIZE: "4"
+  extraCmdArgs: [ "--num-shard","1" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+    requests:
+      cpu: 1
+      memory: 16Gi
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
+    capabilities:
+      add:
+        - SYS_PTRACE
+  readinessProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+  startupProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+vllm:
+  enabled: false
+llm-uservice:
+  TEXTGEN_BACKEND: TGI
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"
diff --git a/CodeGen/kubernetes/helm/rocm-values.yaml b/CodeGen/kubernetes/helm/rocm-values.yaml
new file mode 100644
index 0000000000..0c96b475c2
--- /dev/null
+++ b/CodeGen/kubernetes/helm/rocm-values.yaml
@@ -0,0 +1,41 @@
+# Copyright (c) 2025 Advanced Micro Devices, Inc.
+
+
+tgi:
+  enabled: false
+
+vllm:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: opea/vllm-rocm
+    tag: latest
+  env:
+    HIP_VISIBLE_DEVICES: "0"
+    TENSOR_PARALLEL_SIZE: "1"
+    HF_HUB_DISABLE_PROGRESS_BARS: "1"
+    HF_HUB_ENABLE_HF_TRANSFER: "0"
+    VLLM_USE_TRITON_FLASH_ATTN: "0"
+    VLLM_WORKER_MULTIPROC_METHOD: "spawn"
+    PYTORCH_JIT: "0"
+    HF_HOME: "/data"
+  extraCmd:
+    command: [ "python3", "/workspace/api_server.py" ]
+  extraCmdArgs: [ "--swap-space", "16",
+                  "--disable-log-requests",
+                  "--dtype", "float16",
+                  "--num-scheduler-steps", "1",
+                  "--distributed-executor-backend", "mp" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+  startupProbe:
+    failureThreshold: 180
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
+
+llm-uservice:
+  TEXTGEN_BACKEND: vLLM
+  retryTimeoutSeconds: 720
diff --git a/CodeTrans/kubernetes/helm/README.md b/CodeTrans/kubernetes/helm/README.md
index f4a14e5422..647589b950 100644
--- a/CodeTrans/kubernetes/helm/README.md
+++ b/CodeTrans/kubernetes/helm/README.md
@@ -16,3 +16,150 @@ helm install codetrans oci://ghcr.io/opea-project/charts/codetrans  --set global
 export HFTOKEN="insert-your-huggingface-token-here"
 helm install codetrans oci://ghcr.io/opea-project/charts/codetrans  --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f gaudi-values.yaml
 ```
+
+## Deploy on AMD ROCm using Helm charts from the binary Helm repository
+
+```bash
+mkdir ~/codetrans-k8s-install && cd ~/codetrans-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/CodeTrans/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="mistralai/Mistral-7B-Instruct-v0.3"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/codetrans-k8s-install/GenAIExamples/CodeTrans/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/codetrans-k8s-install/GenAIExamples/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+helm upgrade --install codetrans oci://ghcr.io/opea-project/charts/codetrans \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+helm upgrade --install codetrans oci://ghcr.io/opea-project/charts/codetrans \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-tgi-values.yaml
+```
+
+## Deploy on AMD ROCm using Helm charts from Git repositories
+
+### Creating working dirs
+
+```bash
+mkdir ~/codetrans-k8s-install && cd ~/codetrans-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+git clone https://github.com/opea-project/GenAIInfra.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/CodeGen/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="mistralai/Mistral-7B-Instruct-v0.3"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/codetrans-k8s-install/GenAIExamples/CodeTrans/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/codetrans-k8s-install/GenAIExamples/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+cd ~/codetrans-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update codetrans
+helm upgrade --install codetrans codetrans \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/CodeTrans/kubernetes/helm/rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+cd ~/codetrans-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update codetrans
+helm upgrade --install codetrans codetrans \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml
+```
diff --git a/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml b/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml
new file mode 100644
index 0000000000..3529c00e71
--- /dev/null
+++ b/CodeTrans/kubernetes/helm/rocm-tgi-values.yaml
@@ -0,0 +1,44 @@
+# Copyright (c) 2025 Advanced Micro Devices, Inc.
+
+tgi:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: ghcr.io/huggingface/text-generation-inference
+    tag: "2.4.1-rocm"
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"
+  MAX_INPUT_LENGTH: "1024"
+  MAX_TOTAL_TOKENS: "2048"
+  USE_FLASH_ATTENTION: "false"
+  FLASH_ATTENTION_RECOMPUTE: "false"
+  HIP_VISIBLE_DEVICES: "0"
+  MAX_BATCH_SIZE: "4"
+  extraCmdArgs: [ "--num-shard","1" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+    requests:
+      cpu: 1
+      memory: 16Gi
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
+    capabilities:
+      add:
+        - SYS_PTRACE
+  readinessProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+  startupProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+vllm:
+  enabled: false
+llm-uservice:
+  TEXTGEN_BACKEND: TGI
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"
diff --git a/CodeTrans/kubernetes/helm/rocm-values.yaml b/CodeTrans/kubernetes/helm/rocm-values.yaml
new file mode 100644
index 0000000000..48a99d7e6f
--- /dev/null
+++ b/CodeTrans/kubernetes/helm/rocm-values.yaml
@@ -0,0 +1,42 @@
+# Copyright (c) 2025 Advanced Micro Devices, Inc.
+
+tgi:
+  enabled: false
+
+vllm:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: opea/vllm-rocm
+    tag: latest
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"
+  env:
+    HIP_VISIBLE_DEVICES: "0"
+    TENSOR_PARALLEL_SIZE: "1"
+    HF_HUB_DISABLE_PROGRESS_BARS: "1"
+    HF_HUB_ENABLE_HF_TRANSFER: "0"
+    VLLM_USE_TRITON_FLASH_ATTN: "0"
+    VLLM_WORKER_MULTIPROC_METHOD: "spawn"
+    PYTORCH_JIT: "0"
+    HF_HOME: "/data"
+  extraCmd:
+    command: [ "python3", "/workspace/api_server.py" ]
+  extraCmdArgs: [ "--swap-space", "16",
+                  "--disable-log-requests",
+                  "--dtype", "float16",
+                  "--num-scheduler-steps", "1",
+                  "--distributed-executor-backend", "mp" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+  startupProbe:
+    failureThreshold: 180
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
+
+llm-uservice:
+  TEXTGEN_BACKEND: vLLM
+  retryTimeoutSeconds: 720
+  LLM_MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct"