Qualcomm AI Engine Direct - Adding QNN backend support for the sort core ATen op (#21386)

### Summary
Added support for the `aten.sort` core ATen op for QNN HTP backend.
Implements `aten.sort.default` delegation to QNN HTP by reusing the
existing `TopK` op with `k = dim_size`. Supports both ascending and
descending sort order.

Note that this op faces the same limitations as the existing `TopK` op:

- Only supports sorting along the last dimension (QNN constraint).
- Sort indices are output as `int32`; consuming them with gather in
quantized models may cause `dtype` mismatches. Added a floating point
`sort_and_index` test for this use-case.

### Test plan
```
pytest backends/qualcomm/tests/rework/htp/op/v68/test.py -k "test_sort"


python backends/qualcomm/tests/test_qnn_delegate.py TestQNNQuantizedOperator.test_qnn_backend_sort --soc_model SM8750 --host aisw-vm15-labsd --device 545ee4aa --build_folder build-android

python backends/qualcomm/tests/test_qnn_delegate.py TestQNNFloatingPointOperator.test_qnn_backend_sort --soc_model SM8750 --host aisw-vm15-labsd --device 545ee4aa --build_folder build-android

python backends/qualcomm/tests/test_qnn_delegate.py TestQNNFloatingPointOperator.test_qnn_backend_sort_and_index --soc_model SM8750 --host aisw-vm15-labsd --device 545ee4aa --build_folder build-android
```