[Documentation] How to profile the GPU memory info for a onnxruntime session?

### Describe the documentation issue

How to profile the GPU memory info for a onnxruntime session?
e.g.
```
onnx_session = onnxruntime.InferenceSession(detect_model,sess_options,providers=exec_providers)
print(onnx_session.memory_consumption())
```
Is there a python API to show the GPU memory consumption?

### Page / URL

_No response_

Start by checking the ONNX Runtime Python InferenceSession APIs and existing profiling documentation for GPU memory support. Document the supported way to inspect GPU memory for a session, or clearly state that no Python API exists and identify the available profiling alternative.

Written by the indexing model from the issue text.