Add OnnxDiscrepancyCheck speedup metric with default timing updates

[xadupre]

Describe your changes

Added speedup measurement for OnnxDiscrepancyCheck and updated behavior based on review feedback:

• Changed timing_iterations default from 10 to 5.
• If timing_iterations is set to 0, speedup measurement is skipped.
• Added unit tests to validate the new default and the skip behavior.

Checklist before requesting a review

• Add unit tests for this change.
• Make sure all tests can pass.
• Update documents if necessary.
• Lint and apply fixes to your code by running lintrunner -a
• Is this a user-facing change? If yes, give a description of this change to be included in the release notes.

(Optional) Issue link

[Copilot]

Pull request overview

This PR enhances the OnnxDiscrepancyCheck pass by adding an inference speedup measurement (ONNX vs PyTorch) and introducing configurable warmup/timing iteration settings, with updated defaults and tests to validate the new behavior.

Changes:

• Added warmup_iterations and timing_iterations config parameters (defaulting timing_iterations to 5) and implemented speedup measurement with an option to skip when timing_iterations=0.
• Updated session/device setup to target the configured accelerator (with CPU fallback) and run PyTorch on the matched torch device.
• Added unit tests to validate the new default and the skip behavior.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
olive/passes/onnx/discrepancy_check.py	Adds speedup timing, new config params/defaults, and device-aware session/model handling.
test/passes/onnx/test_discrepancy_check.py	Adds tests for the new timing_iterations default and the “skip when 0” behavior.