fix qdq utils issues and remove global cast replacements

[nvluxiaoz]

What does this PR do?

Type of change: Bug fix

Overview: While attempting to transformers, onnx, torch and modelopt, it is shown the following:

• Original Reshape - Cast - Transpose becomes Reshape - Transpose, so there is no required Cast for int4
• Global cast replacement to FP16 is not required since it will affect other Modules

Usage

# Add a code snippet demonstrating how to use this

Testing

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?: No
• Did you add or update any necessary documentation?: No
• Did you update Changelog?: No

Additional Information

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[codecov]

Codecov Report

❌ Patch coverage is 90.00000% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 74.31%. Comparing base (8cf516e) to head (b167cd0).

Files with missing lines	Patch %	Lines
modelopt/onnx/quantization/qdq_utils.py	90.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #489      +/-   ##
==========================================
+ Coverage   73.46%   74.31%   +0.84%     
==========================================
  Files         180      180              
  Lines       18161    18149      -12     
==========================================
+ Hits        13342    13487     +145     
+ Misses       4819     4662     -157     

☔ 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.

[nvluxiaoz]

@ajrasane Do you know if this pipeline is counted as successful, and if not, what fails? Thanks!

[ajrasane]

All the checks seem to have passed. But your commits are not verified. Could you once check these instructions and force push a new verified commit for your changes?
https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md#%EF%B8%8F-signing-your-work

[nvluxiaoz]

Thanks. @ajrasane it is now updated. Can you help merge this once pipeline is successful again?