✨ Add .devcontainer Configuration for TorchServe Development Environment

.devcontainer/devcontainer.json

@@ -0,0 +1,27 @@
+{
+    "name": "TorchServe Dev Environment",
+    "build": {
+        "dockerfile": "../docker/Dockerfile",
+        "context": "..",
+        "args": {
+            "BASE_IMAGE": "ubuntu:20.04",
+            "PYTHON_VERSION": "3.9",
+            "BRANCH_NAME": "master",
+            "REPO_URL": "https://github.com/pytorch/serve.git",
+            "CUDA_VERSION": ""
+        }
+    },
+    "customizations": {
+        "vscode": {
+            "extensions": [
+                "ms-python.python"
+            ]
+        }
+    },
+    "runArgs": [
+        // ACTION NEEDED: uncomment the next line if your local machine has GPUs available
+//        "--gpus", "all",
+        // Enable the docker container to access system resources
+        "--ipc", "host"
+    ]
+}

CONTRIBUTING.md

@@ -81,6 +81,10 @@ Refer to the documentation [here](docs/torchserve_on_win_native.md).
 
 For information about the model archiver, see [detailed documentation](model-archiver/README.md).
 
+### Using Visual Studio Code Dev Containers
+
+You can also set up a development environment for TorchServe using Visual Studio Code Dev Containers. This approach provides a fully-isolated, Docker-based environment that simplifies setup and ensures consistency across different development machines. Follow the guide in the [Development Environment with VS Code Dev Containers](docker/README.md#development-environment-with-vs-code-dev-containers) section of the Docker README for setup instructions and customization options.
+
 ### What to Contribute?
 
 ### A good first issue

docker/README.md

@@ -12,6 +12,7 @@ TorchServe now enforces token authorization enabled and model API control disabl
 * [Create TorchServe docker image](#create-torchserve-docker-image)
 * [Create torch-model-archiver from container](#create-torch-model-archiver-from-container)
 * [Running TorchServe docker image in production](#running-torchserve-in-a-production-docker-environment)
+* [Development Environment with VS Code Dev Containers](#development-environment-with-vs-code-dev-containers)
 
 # Prerequisites
 
@@ -304,6 +305,54 @@ docker run --rm --shm-size=1g \
         --mount type=bind,source=/path/to/model/store,target=/tmp/models <container> torchserve --model-store=/tmp/models
 ```
 
+# Development Environment with VS Code Dev Containers
+
+This section provides a guide on setting up a development environment for TorchServe using Visual Studio Code Dev Containers.
+
+## Setup Instructions
+
+1. **Install the Dev Containers Extension**  
+   In Visual Studio Code, search for "Dev Containers" in the Extensions marketplace and install it.
+
+   ![Dev Containers Extension Installation](https://github.com/user-attachments/assets/16e1fd10-b20e-4ef4-a16f-0f544d233ba6)
+
+2. **Open in Container**  
+   After installation, you will see a pop-up similar to the one in the screenshot. Click the "Reopen in Container" button to start the development environment inside a Docker container.
+
+   ![Reopen in Container](https://github.com/user-attachments/assets/31c3c090-2808-4e55-8d2e-89d4ab40649f)
+
+## Customizing the Development Environment
+
+To use a GPU-based container or make other modifications, update the `.devcontainer/devcontainer.json` file. Here’s an example configuration for a GPU-enabled environment:
+
+```json
+{
+    "name": "TorchServe Dev Environment",
+    "build": {
+        "dockerfile": "../docker/Dockerfile",
+        "context": "..",
+        "args": {
+            "BASE_IMAGE": "nvidia/cuda:12.1.1-base-ubuntu20.04",
+            "PYTHON_VERSION": "3.9",
+            "BRANCH_NAME": "master",
+            "REPO_URL": "https://github.com/pytorch/serve.git",
+            "CUDA_VERSION": "cu121"
+        }
+    },
+    "customizations": {
+        "vscode": {
+            "extensions": [
+                "ms-python.python"
+            ]
+        }
+    },
+    "runArgs": [
+        "--gpus", "all",
+        "--ipc", "host"
+    ]
+}
+```
+
 # Example showing serving model using Docker container
 
 [This](../examples/image_classifier/mnist/Docker.md) is an example showing serving MNIST model using Docker.