Upgrade ORT to 1.24

Signed-off-by: gcunhase <4861122+gcunhase@users.noreply.github.com>

Author: gcunhase

CHANGELOG.rst

@@ -4,6 +4,10 @@ NVIDIA Model Optimizer Changelog (Linux)
 0.43 (2026-03-xx)
 ^^^^^^^^^^^^^^^^^
 
+**Bug Fixes**
+
+- Upgraded ORT to 1.24.2 to solve various bugs: 5615343, 5597780, 5371126.
+
 **New Features**
 
 - User does not need to manually register MOE modules to cover experts calibration coverage in PTQ workflow.

docs/source/getting_started/_installation_for_Linux.rst

@@ -20,7 +20,7 @@ Latest Model Optimizer (``nvidia-modelopt``) currently has the following system
 +-------------------------+-----------------------------+
 | TensorRT-LLM (Optional) |  >=1.0                      |
 +-------------------------+-----------------------------+
-| ONNX Runtime (Optional) |  1.22                       |
+| ONNX Runtime (Optional) |  1.24                       |
 +-------------------------+-----------------------------+
 | TensorRT (Optional)     |  >=10.0                     |
 +-------------------------+-----------------------------+

setup.py

@@ -49,7 +49,7 @@
         "onnx~=1.19.0",
         "onnxconverter-common~=1.16.0",
         "onnxruntime~=1.22.0 ; platform_machine == 'aarch64' or platform_system == 'Darwin'",
-        "onnxruntime-gpu~=1.22.0 ; platform_machine != 'aarch64' and platform_system != 'Darwin'",
+        "onnxruntime-gpu~=1.24.2 ; platform_machine != 'aarch64' and platform_system != 'Darwin'",
         "onnxscript",  # For autocast opset conversion and test_onnx_dynamo_export unit test
         "onnxslim>=0.1.76",
         "polygraphy>=0.49.22",