Bump SMD version to enable custom workflow deployment.

[cj-zhang]

Description of changes:

• Bump custom workflow deployment to use SMD 3.2 image
• Custom workflow deployment fails because only introduced in sagemaker 2.44.0 (https://github.com/aws/sagemaker-python-sdk/releases/tag/v2.244.0)
• custom workflow deployment is using SMD 3.0 which only has sagemaker 2.42.0 (SMD 3.0 changelog)

Testing done:

• Deployed workflow IC successfully

INFO:sagemaker:Creating endpoint-config with name llama-mistral-endpoint-34caa6b8577611f083385a17-1751482587-429a
INFO:sagemaker:Creating endpoint with name llama-mistral-endpoint-34caa6b8577611f083385a17-1751482587-429a
----!
INFO:sagemaker:Creating model with name: custom-orchestrator-388ddbf8577611f083385a1715d0cb10
INFO:sagemaker:Creating inference component with name custom-orchestrator-388ddbf8577611f083385a1715d0cb10 for endpoint llama-mistral-endpoint-34caa6b8577611f083385a17-1751482587-429a
---------------------!
ModelBuilder: DEBUG:     ModelBuilder metrics emitted.
ModelBuilder: DEBUG:     ModelBuilder metrics emitted.

Merge Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.

General

• I have read the CONTRIBUTING doc
• I certify that the changes I am introducing will be backward compatible, and I have discussed concerns about this, if any, with the Python SDK team
• I used the commit message format described in CONTRIBUTING
• I have passed the region in to all S3 and STS clients that I've initialized as part of this change.
• I have updated any necessary documentation, including READMEs and API docs (if appropriate)

Tests

• I have added tests that prove my fix is effective or that my feature works (if appropriate)
• I have added unit and/or integration tests as appropriate to ensure backward compatibility of the changes
• I have checked that my tests are not configured for a specific region or account (if appropriate)
• I have used unique_name_from_base to create resource names in integ tests (if appropriate)
• If adding any dependency in requirements.txt files, I have spell checked and ensured they exist in PyPi

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.