Merge pull request #226584 from dem108/patch-17

Clarify how to deploy more than 1500 files

Author: prmerger-automator[bot]

articles/machine-learning/how-to-deploy-online-endpoints.md

@@ -376,7 +376,10 @@ For supported general-purpose and GPU instance types, see [Managed online endpoi
 
 ### Use more than one model
 
-Currently, you can specify only one model per deployment in the YAML. If you've more than one model, when you register the model, copy all the models as files or subdirectories into a folder that you use for registration. In your scoring script, use the environment variable `AZUREML_MODEL_DIR` to get the path to the model root folder. The underlying directory structure is retained. For an example of deploying multiple models to one deployment, see [Deploy multiple models to one deployment](https://github.com/Azure/azureml-examples/blob/main/cli/endpoints/online/custom-container/minimal/multimodel).
+Currently, you can specify only one model per deployment in the YAML. If you have more than one model, when you register the model, copy all the models as files or subdirectories into a folder that you use for registration. In your scoring script, use the environment variable `AZUREML_MODEL_DIR` to get the path to the model root folder. The underlying directory structure is retained. For an example of deploying multiple models to one deployment, see [Deploy multiple models to one deployment](https://github.com/Azure/azureml-examples/blob/main/cli/endpoints/online/custom-container/minimal/multimodel).
+
+> [!TIP]
+> If you have more than 1500 files to register, you may consider compressing the files or subdirectories as .tar.gz when registering the model. To consume the models, you can uncompress the files or subdirectories in the init() function from the scoring script. In this case, uncompression happens once in the initialization stage.
 
 ## Understand the scoring script