onnxruntime

b0279b14 - [DORT] Enable Dynamic Shape in DORT and Use Different InferenceSession's when Inputs Are Not Compatible (#16753)

[DORT] Enable Dynamic Shape in DORT and Use Different InferenceSession's when Inputs Are Not Compatible (#16753) Sometimes, ONNX exporter generates rank- or shape-dependent sub-graphs. Thus, error could occur when running the ONNX model with different inputs. This PR ([78e736d](https://github.com/microsoft/onnxruntime/pull/16753/commits/78e736d857fa168653bab10afa1d1aefa4abbfba)) addresses this problem by - if needed, exporting multiple ONNX models with different inputs for the same GraphModule. - implementing a naive mechanism to determine of existing ONNX models (and the associated InferenceSession) can be reused. On the other hand, in the second commit [b5a9b5f](https://github.com/microsoft/onnxruntime/pull/16753/commits/b5a9b5f849b139ba287dc3d2545d66c982a9def3), this PR also enables dynamic shapes in DORT by - passing dynamic_shapes = True to exporter (see how DEFAULT_DYNAMIC_BACKEND is created) - calling torch._dynamo.optimize(dynamic_ort_aot, dynamic=True) (see how dynamic_ort_aot is created).