titaiwang 957312a4cf [ONNX] Relax unsupported node analysis on complex dtype (#113785) ... In cases like #113444, users usually stop at UnsupportedNodeAnalysis with unsupported nodes information. Although in SARIF, they can clearly see it's due to lack of COMPLEX support, in screen error message, it's only showing original FX node name, such as `aten.mul.Tensor`. ~~This PR catches the information from diagnostic messages and reveal it to users.~~ The root cause is that UnsupportedNodeAnalysis is leveraging on `onnxfunction_dispatcher.get_function_overloads()` to decide if an ATen is supported or not. However, in `onnxfunction_dispatcher.get_function_overloads()`, lacking of complex function support is considered unsupported. This PR defines Unsupported FX nodes as not in registry. Pull Request resolved: https://github.com/pytorch/pytorch/pull/113785 Approved by: https://github.com/thiagocrepaldi		2023-11-17 20:11:20 +00:00
..
test_dynamo_with_onnxruntime_backend.py	[ONNX] Support torch.compile(backend="onnxrt", options=OrtBackendOptions(...)) (#107973)	2023-08-26 18:20:18 +00:00
test_exporter_api.py	Rename torch.onnx.ExportOutput* to ONNXProgram* (#112263)	2023-11-06 22:27:15 +00:00
test_registry_dispatcher.py	[ONNX] Relax unsupported node analysis on complex dtype (#113785)	2023-11-17 20:11:20 +00:00