[5615343,5597780,5371126] Upgrade ORT to 1.24

[gcunhase]

What does this PR do?

Type of change: Bug fix

Overview: Upgrade ORT to 1.24.x to fix various bugs (5615343, 5597780, 5371126).

TODO: Verify no regressions by bumping ORT once @ajrasane is back

Usage

See each bug.

Testing

See each bug.

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?: Yes

Summary by CodeRabbit

Bug Fixes

• Upgraded ONNX Runtime to version 1.24.2, addressing multiple reported issues
• Updated system requirements and installation documentation to reflect the new ONNX Runtime version

[coderabbitai]

📝 Walkthrough

Walkthrough

ONNX Runtime dependencies are updated from version 1.22.x to 1.24.2 across the codebase. The upgrade is documented in the changelog with references to specific bug fixes, reflected in Linux installation documentation, and applied to Python package configuration.

Changes

Cohort / File(s)	Summary
ONNX Runtime Version Upgrade CHANGELOG.rst, docs/source/getting_started/_installation_for_Linux.rst, setup.py	Version bump from 1.22.x to 1.24.2 across release notes, installation documentation, and dependency specifications to address bugs (5615343, 5597780, 5371126). Platform constraint on GPU variant preserved.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly references the bug IDs and specifies the main change: upgrading ORT to version 1.24, which directly matches the PR's objective of fixing those specific issues.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@docs/source/getting_started/_installation_for_Linux.rst`:
- Line 23: The docs table was updated to show "ONNX Runtime (Optional) | 1.24"
but setup.py still pins onnxruntime to the aarch64-specific constraint
"~=1.22.0", so update one of them for consistency: either (A) adjust the docs
entry text in docs/source/getting_started/_installation_for_Linux.rst to
indicate 1.24 applies to x86_64 only (or call out the aarch64 exception),
referencing the table row "ONNX Runtime (Optional) |  1.24", or (B) fix setup.py
to remove/relax the onnxruntime aarch64 pin (the pinned requirement string
"~=1.22.0" in setup.py) so it matches 1.24; make sure the doc and setup.py agree
and mention the aarch64 caveat if the underlying aarch64 fix is not yet applied.

In `@setup.py`:
- Around line 51-52: The setup.py dependency entries currently pin
"onnxruntime~=1.22.0 ; platform_machine == 'aarch64' or platform_system ==
'Darwin'" while GPU uses "onnxruntime-gpu~=1.24.2 ; platform_machine !=
'aarch64' and platform_system != 'Darwin'": either update the aarch64/Darwin CPU
pin to "~=1.24.2" to match the GPU line and the Linux docs, or add an inline
comment next to the "onnxruntime~=1.22.0 ..." entry explaining why
aarch64/Darwin must stay at 1.22.0 (e.g., known incompatibility), and update the
installation docs reference to ONNX Runtime 1.24 in _installation_for_Linux.rst
if you bump the version so docs and requirements remain consistent.

---

ℹ️ Review info

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 75b5da9 and e529698.

📒 Files selected for processing (3)

• CHANGELOG.rst
• docs/source/getting_started/_installation_for_Linux.rst
• setup.py

[codecov]

Codecov Report

❌ Patch coverage is 66.66667% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 72.04%. Comparing base (75b5da9) to head (13c758d).
⚠️ Report is 8 commits behind head on main.

Files with missing lines	Patch %	Lines
modelopt/onnx/__init__.py	66.66%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #928      +/-   ##
==========================================
- Coverage   73.11%   72.04%   -1.07%     
==========================================
  Files         205      207       +2     
  Lines       22294    22694     +400     
==========================================
+ Hits        16300    16350      +50     
- Misses       5994     6344     +350     

☔ 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.

[gcunhase]

@ajrasane to check this PR for any accuracy regressions (as observed with ORT 1.23). Thanks!