[5680954,5620660@2][ONNX][Autocast] Update value info in converted graph

[gcunhase]

What does this PR do?

Type of change: Bug fix

Overview: Some tensor's precision weren't set in the ONNX graph (value_info) when converting the model with Autocast. This caused ONNX-Graphsurgeon to incorrectly interpret those precisions in gs.import_onnx(ModelProto), which caused quantization of the converted model to fail.

Usage

$ python -m modelopt.onnx.autocast --onnx_path=$MODEL_NAME.onnx --keep_io_types
$ python -m modelopt.onnx.quantization --onnx_path=$MODEL_NAME.fp16.onnx --calibration_eps cpu

Testing

See bug 5680954@12.

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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.64%. Comparing base (261858c) to head (6832f24).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #611      +/-   ##
==========================================
- Coverage   74.80%   74.64%   -0.16%     
==========================================
  Files         183      183              
  Lines       18626    18546      -80     
==========================================
- Hits        13933    13844      -89     
- Misses       4693     4702       +9     

☔ 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.

[galagam]

Did you find the location where we update self.value_info_map instead of self.model.graph.value_info ?
Maybe graph outputs/inputs?

This fix is a little patchy IMO.