Integrate Automated QDQ placement tool - part 2.2 (#845)

## What does this PR do?

This PR implements RegionSearch class. RegionSearch could help partition
big ONNX model into small region. QDQ autouning will be performed on the
regions.

**Overview:** ?

## Usage
<!-- You can potentially add a usage example below. -->

```python
# Add a code snippet demonstrating how to use this
```

## Testing
<!-- Mention how have you tested your change if applicable. -->

## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->

- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
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?**: No, document
updates is in Part 4.
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
CHANGELOG will be updated when all changes are ready.

## Additional Information
<!-- E.g. related issue. -->

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

## Release Notes

**Refactor**
* Improved ONNX quantization backend with new optimization framework and
extensive test coverage to enhance internal graph processing
capabilities.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Will Guo <willg@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>

Author: willg-nv