fix(test): pin ONNX IR version 8 in ort quantize test

modelopt[onnx] pulls in onnxruntime-gpu~=1.22.0 as a dependency on all
Python versions.  Newer ONNX packages (1.19+) default model.ir_version
to 12, but onnxruntime-gpu 1.22.0 only supports up to IR version 10,
causing test_ort_quantize_int8_produces_output_file to fail on the GPU
CI for py3.11, py3.12, and py3.13.

Pin model.ir_version = 8 (the minimum required for opset 17) before
saving the test model so the calibration InferenceSession succeeds with
any onnxruntime version that supports IR ≤ 10.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: ivanbasov

code/tests/test_onnx_quant_workflow.py

@@ -237,6 +237,9 @@ def test_ort_quantize_int8_produces_output_file(self):
         node = oh.make_node("Gemm", inputs=["dets", "W", "B"], outputs=["Y"])
         graph = oh.make_graph([node], "tiny", [X], [Y], initializer=[W, B])
         model = oh.make_model(graph, opset_imports=[oh.make_opsetid("", 17)])
+        # Pin to IR version 8 (opset-17 minimum).  Newer ONNX packages default to
+        # IR version 12, which onnxruntime-gpu 1.22.0 (a modelopt dependency) rejects.
+        model.ir_version = 8
         onnx.checker.check_model(model)
 
         calib = np.random.randint(0, 2, (8, 4), dtype=np.uint8)