Integrate Automated QDQ placement tool - Part 1

[willg-nv]

What does this PR do?

Type of change: new feature

Overview: This PR integrates an automatical QDQ placment tool into ModelOpt.

This PR is the 1/4 parts of the change, it contains the following changes:

1. Defines common types: Region, RegionType, Error types
2. Defines InsertionPoints (the logical localtion to place QDQ pairs), InsertionScheme (a set of insertion points)
3. Unit tests for new types

Part 1: #701
Part 2: #702
Part 3: #703
Part 4: #704

Usage

        # Region type usage:
        region = Region(region_id=1, level=0, region_type=RegionType.LEAF)
        assert region.get_id() == 1
        assert region.get_level() == 0
        region.add_node(1) # 1 is the index of ONNX graph node
        ...

        point = NodeInputInsertionPoint(node_index=0, input_index=2)
        assert point.node_index == 0 # relative node index in region
        assert point.input_index == 2 # relative input tensor index in specific node
        resolved = point.resolve(region, graph)
        ...

Testing

Implement unit tests, all tests could get passed.

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?: No, document change will be included in part 4.
• Did you update Changelog?: No, this could be done when all parts of the change are merged.

Additional Information

Summary by CodeRabbit

• New Features

  • Added foundational autotuner infrastructure for quantization optimization, including region hierarchies and insertion scheme management.
  • Introduced insertion point system for managing quantize/dequantize operation placement across ONNX graph regions.
  • Added utility functions for tensor consumer mapping and boolean operation identification.

• Tests

  • Added comprehensive test coverage for autotuner components, insertion points, and region management.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[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.

[willg-nv]

Hi @gcunhase, could you help me review this PR? thanks!

[ajrasane]

LGTM from my side. Will wait for @gcunhase review.

[gcunhase]

LGTM, added a few comments, thanks.

[ajrasane]

LGTM

[gcunhase]

LGTM, other changes can be done in #702.

[codecov]

Codecov Report

❌ Patch coverage is 91.28065% with 32 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.16%. Comparing base (81b67dd) to head (09a91a8).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
modelopt/onnx/quantization/autotune/common.py	81.81%	24 Missing ⚠️
...opt/onnx/quantization/autotune/insertion_points.py	96.61%	7 Missing ⚠️
modelopt/onnx/quantization/graph_utils.py	92.30%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #701      +/-   ##
==========================================
+ Coverage   73.82%   74.16%   +0.33%     
==========================================
  Files         193      195       +2     
  Lines       19745    20111     +366     
==========================================
+ Hits        14577    14915     +338     
- Misses       5168     5196      +28     

☔ 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.