[DOCS] [IRD Vision] added instruction to run gpu npu in helm (#2187)

Author: sajeevrajput

manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/pallet-defect-detection/get-started/deploy-with-helm.md

@@ -171,6 +171,21 @@
    ```
 
    > **Note:**- This would start the pipeline. You can view the inference stream on WebRTC by opening a browser and navigating to https://<HOST_IP>:30443/mediamtx/pdd/ for Pallet Defect Detection. If you're running helm using an `NGINX_HTTPS_PORT` other than the default 30443, replace `<HOST_IP>` with `<HOST_IP>:<NGINX_HTTPS_PORT>`.
+   
+   ### Starting GPU and NPU based pipelines
+   For GPU and NPU based pipelines, ensure you have done the necessary [setup](../how-to-guides/use-gpu-for-inference.md#deploying-with-helm) from here, and start the respective pipelines as following.
+
+      **For GPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p pallet_defect_detection_gpu
+      ```
+
+      **For NPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p pallet_defect_detection_npu
+      ```
 
 5. Get status of pipeline instance(s) running.
 

manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/pcb-anomaly-detection/get-started/deploy-with-helm.md

@@ -163,6 +163,21 @@
    > **Note:** This would start the pipeline. You can view the inference stream on WebRTC by
    > opening a browser and navigating to `https://<HOST_IP>:30443/mediamtx/anomaly/` for PCB Anomaly Detection.
    > If you're running helm using an NGINX_HTTPS_PORT other than the default 30443, replace 30443 with <NGINX_HTTPS_PORT>.
+   
+   ### Starting GPU and NPU based pipelines
+   For GPU and NPU based pipelines, ensure you have done the necessary [setup](../how-to-guides/use-gpu-for-inference.md#deploying-with-helm) from here, and start the respective pipelines as following.
+   
+      **For GPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p pcb_anomaly_detection_gpu
+      ```
+
+      **For NPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p pcb_anomaly_detection_npu
+      ```
 
 5. Get status of pipeline instance(s) running.
 

manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/weld-porosity/get-started/deploy-with-helm.md

@@ -161,6 +161,21 @@
 
    > **Note:**- This would start the pipeline. You can view the inference stream on WebRTC by opening a browser and navigating to https://<HOST_IP>:30443/mediamtx/weld/
    >If you're running helm using an `NGINX_HTTPS_PORT` other than the default 30443, replace `<HOST_IP>` with `<HOST_IP>:<NGINX_HTTPS_PORT>`.
+   
+   ### Starting GPU and NPU based pipelines
+   For GPU and NPU based pipelines, ensure you have done the necessary [setup](../how-to-guides/use-gpu-for-inference.md#deploying-with-helm) from here, and start the respective pipelines as following.
+
+      **For GPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p weld_porosity_classification_gpu
+      ```
+
+      **For NPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p weld_porosity_classification_npu
+      ```
 
 5. Get status of pipeline instance(s) running.
 

manufacturing-ai-suite/industrial-edge-insights-vision/docs/user-guide/worker-safety-gear-detection/get-started/deploy-with-helm.md

@@ -159,6 +159,21 @@
    > **Note:** This would start the pipeline. You can view the inference stream on WebRTC by
    > opening a browser and navigating to `https://<HOST_IP>:30443/mediamtx/worker_safety/` for Worker Safety gear detection.
    > If you're running helm using an NGINX_HTTPS_PORT other than the default 30443, replace 30443 with <NGINX_HTTPS_PORT>.
+   
+   ### Starting GPU and NPU based pipelines
+   For GPU and NPU based pipelines, ensure you have done the necessary [setup](../how-to-guides/use-gpu-for-inference.md#deploying-with-helm) from here, and start the respective pipelines as following.
+
+      **For GPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p worker_safety_gear_detection_gpu
+      ```
+
+      **For NPU-based pipelines:**
+
+      ```sh
+      ./sample_start.sh helm -p worker_safety_gear_detection_npu
+      ```
 
 5. Get status of pipeline instance(s) running.