onnxruntime

8f6c25f7 - [QNN EP] Handle 0-dim tensor for Concat. (#26644)

[QNN EP] Handle 0-dim tensor for Concat. (#26644) ### Description <!-- Describe your changes. --> Define a util function `DoesConcatInputShapeContainZero` to check whether given tensor has 0-dim in shape. To restrict the impact, current implementation only skip constructing such tensor for Concat. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> There may exist tensor with 0-dim in shape, especially for Concat's inputs. Such null inputs often exist in models saved from PyTorch. Since QNN could not execute empty tensors, they must be explicitly handled.