fix: pass in inference_ami_version to model_based endpoint type (aws#5043)

* fix: pass in inference_ami_version to model_based endpoint type

* documentation: update contributing.md w/ venv instructions and pip install fixes

---------

Co-authored-by: Zhaoqi <[email protected]>

Author: timkuo-amazon

CONTRIBUTING.md

@@ -61,6 +61,10 @@ Before sending us a pull request, please ensure that:
    1. Follow the instructions at [Modifying an EBS Volume Using Elastic Volumes (Console)](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/requesting-ebs-volume-modifications.html#modify-ebs-volume) to increase the EBS volume size associated with the newly created EC2 instance.
    1. Wait 5-10min for the new EBS volume increase to finalize.
    1. Allow EC2 to claim the additional space by stopping and then starting your EC2 host.
+2. Set up a venv to manage dependencies:
+   1. `python -m venv ~/.venv/myproject-env` to create the venv
+   2. `source ~/.venv/myproject-env/bin/activate` to activate the venv
+   3. `deactivate` to exit the venv
 
 
 ### Pull Down the Code
@@ -74,8 +78,8 @@ Before sending us a pull request, please ensure that:
 ### Run the Unit Tests
 
 1. Install tox using `pip install tox`
-1. Install coverage using `pip install .[test]`
-1. cd into the sagemaker-python-sdk folder: `cd sagemaker-python-sdk` or `cd /environment/sagemaker-python-sdk`
+1. cd into the github project sagemaker-python-sdk folder: `cd sagemaker-python-sdk` or `cd /environment/sagemaker-python-sdk`
+1. Install coverage using `pip install '.[test]'`
 1. Run the following tox command and verify that all code checks and unit tests pass: `tox tests/unit`
 1. You can also run a single test with the following command: `tox -e py310 -- -s -vv <path_to_file><file_name>::<test_function_name>`
 1. You can run coverage via runcvoerage env : `tox -e runcoverage -- tests/unit` or `tox -e py310 -- tests/unit --cov=sagemaker --cov-append --cov-report xml`

src/sagemaker/model.py

@@ -1492,6 +1492,9 @@ def deploy(
                     }
             model_reference_arn (Optional [str]): Hub Content Arn of a Model Reference type
                 content (default: None).
+            inference_ami_version (Optional [str]): Specifies an option from a collection of preconfigured
+             Amazon Machine Image (AMI) images. For a full list of options, see:
+             https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_ProductionVariant.html
         Raises:
              ValueError: If arguments combination check failed in these circumstances:
                 - If no role is specified or
@@ -1743,6 +1746,7 @@ def deploy(
                 model_data_download_timeout=model_data_download_timeout,
                 container_startup_health_check_timeout=container_startup_health_check_timeout,
                 routing_config=routing_config,
+                inference_ami_version=inference_ami_version,
             )
             if endpoint_name:
                 self.endpoint_name = endpoint_name

tests/unit/sagemaker/model/test_deploy.py

@@ -130,6 +130,7 @@ def test_deploy(name_from_base, prepare_container_def, production_variant, sagem
         model_data_download_timeout=None,
         container_startup_health_check_timeout=None,
         routing_config=None,
+        inference_ami_version=None,
     )
 
     sagemaker_session.create_model.assert_called_with(
@@ -192,6 +193,7 @@ def test_deploy_accelerator_type(
         model_data_download_timeout=None,
         container_startup_health_check_timeout=None,
         routing_config=None,
+        inference_ami_version=None,
     )
 
     sagemaker_session.endpoint_from_production_variants.assert_called_with(
@@ -519,6 +521,7 @@ def test_deploy_serverless_inference(production_variant, create_sagemaker_model,
         model_data_download_timeout=None,
         container_startup_health_check_timeout=None,
         routing_config=None,
+        inference_ami_version=None,
     )
 
     sagemaker_session.endpoint_from_production_variants.assert_called_with(
@@ -956,6 +959,7 @@ def test_deploy_customized_volume_size_and_timeout(
         model_data_download_timeout=model_data_download_timeout_sec,
         container_startup_health_check_timeout=startup_health_check_timeout_sec,
         routing_config=None,
+        inference_ami_version=None,
     )
 
     sagemaker_session.create_model.assert_called_with(
@@ -1006,6 +1010,7 @@ def test_deploy_with_resources(sagemaker_session, name_from_base, production_var
         model_data_download_timeout=None,
         container_startup_health_check_timeout=None,
         routing_config=None,
+        inference_ami_version=None,
     )
     sagemaker_session.endpoint_from_production_variants.assert_called_with(
         name=name_from_base(MODEL_NAME),