Merge pull request #466 from dhanvia/dhanvia/update-byoc-docs

Added a section to notify the customer to use CLI or SDK for configuring custom environments in BYOC Scenarios

Author: Court72

articles/machine-learning/how-to-deploy-custom-container.md

@@ -337,7 +337,10 @@ In this case, when you create a deployment, your model is located under the foll
 You can optionally configure your `model_mount_path` value. By adjusting this setting, you can change the path where the model is mounted.
 
 > [!IMPORTANT]
-> The `model_mount_path` value must be a valid absolute path in Linux (the OS of the container image).
+> The `model_mount_path` value must be a valid absolute path in Linux (in the guest OS of the container image).
+
+> [!IMPORTANT]
+> `model_mount_path` is usable only in BYOC (Bring your own container) scenario. In BYOC scenario, the environment that the online deployment uses must have [`inference_config` parameter](#the-inference_config-parameter) configured. You can use Azure ML CLI or Python SDK to specify `inference_config` parameter when creating the environment. Studio UI currently doesn't support specifying this parameter.
 
 When you change the value of `model_mount_path`, you also need to update the `MODEL_BASE_PATH` environment variable. Set `MODEL_BASE_PATH` to the same value as `model_mount_path` to avoid a failed deployment due to an error about the base path not being found.
 

articles/machine-learning/reference-yaml-deployment-managed-online.md

@@ -31,7 +31,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 | `tags` | object | Dictionary of tags for the deployment. | | |
 | `endpoint_name` | string | **Required.** Name of the endpoint to create the deployment under. | | |
 | `model` | string or object | The model to use for the deployment. This value can be either a reference to an existing versioned model in the workspace or an inline model specification. <br><br> To reference an existing model, use the `azureml:<model-name>:<model-version>` syntax. <br><br> To define a model inline, follow the [Model schema](reference-yaml-model.md#yaml-syntax). <br><br> As a best practice for production scenarios, you should create the model separately and reference it here. <br><br> This field is optional for [custom container deployment](how-to-deploy-custom-container.md) scenarios.| | |
-| `model_mount_path` | string | The path to mount the model in a custom container. Applicable only for [custom container deployment](how-to-deploy-custom-container.md) scenarios. If the `model` field is specified, it's mounted on this path in the container. | | |
+| `model_mount_path` | string | The path to mount the model in a custom container. Applicable only for [custom container deployment](how-to-deploy-custom-container.md) scenarios, where environment has `inference_config` configured. If the `model` field is specified, it's mounted on this path in the container. | | |
 | `code_configuration` | object | Configuration for the scoring code logic. <br><br> This field is optional for [custom container deployment](how-to-deploy-custom-container.md) scenarios. | | |
 | `code_configuration.code` | string | Local path to the source code directory for scoring the model. | | |
 | `code_configuration.scoring_script` | string | Relative path to the scoring file in the source code directory. | | |