ONNX save fix

[i-riyad]

What does this PR do?

Type of change: Bug

Overview: get_onnx_bytes api is error prone as it returns only the protobuf info. If model has any external data, they get discarded! We have to use get_onnx_bytes_and_metadata and provide example for users to correctly write ONNX model to disk.

Usage

This would be proper way to save ONNX model bytes with/without external data.

    onnx_bytes, _ = get_onnx_bytes_and_metadata(
        model=model,
        dummy_input=(input_tensor,),
        weights_dtype=weights_dtype,
        model_name=model_name,
    )
    onnx_bytes_obj = OnnxBytes.from_bytes(onnx_bytes)

    # Write the onnx model to the specified directory without cleaning it
    onnx_bytes_obj.write_to_disk(os.path.dirname(onnx_save_path), clean_dir=False)

Testing

N/A. Existing tests are modified.

Before your PR is "Ready for review"

• Make sure you read and follow Contributor guidelines and your commits are signed.
• Is this change backward compatible?: Yes
• Did you write any new necessary tests?: Yes
• Did you add or update any necessary documentation?: Yes
• Did you update Changelog?: Yes

Additional Information

https://nvbugspro.nvidia.com/bug/5618246/4

[codecov]

Codecov Report

❌ Patch coverage is 18.18182% with 9 lines in your changes missing coverage. Please review.
✅ Project coverage is 73.43%. Comparing base (72f23dc) to head (eed985e).
⚠️ Report is 12 commits behind head on main.

Files with missing lines	Patch %	Lines
modelopt/torch/_deploy/utils/torch_onnx.py	18.18%	9 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #496      +/-   ##
==========================================
- Coverage   73.43%   73.43%   -0.01%     
==========================================
  Files         180      180              
  Lines       18146    18144       -2     
==========================================
- Hits        13326    13324       -2     
  Misses       4820     4820              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.