[QNN-EP] Einsum QDQ tests followup: node selector

[1duo]

[QNN-EP] Einsum QDQ tests followup: node selector.

Verified now Einsum QDQ tests are running with QNN_DATATYPE_UFIXED_POINT_8:

2025-05-06 11:22:09.738247549 [V:onnxruntime:qdq_model_logger, qnn_model_wrapper.cc:305 ComposeQnnGraph] Qnn_OpConfig node name: node_token_15 package_name: qti.aisw QNN_op_type: MatMul num_of_inputs: 2 num_of_outputs: 1 num_of_params: 2
 node_inputs:
 name=node id=2 version=1 type=QNN_TENSOR_TYPE_NATIVE dataFormat=0 dataType=QNN_DATATYPE_UFIXED_POINT_8 rank=2 dimensions=(2 3 ) memType=QNN_TENSORMEMTYPE_RAW quantizeParams: encodingDefinition=QNN_DEFINITION_DEFINED quantizationEncoding=QNN_QUANTIZATION_ENCODING_SCALE_OFFSET scale=0.000980392 offset=-102
 name=node_token_6 id=4 version=1 type=QNN_TENSOR_TYPE_NATIVE dataFormat=0 dataType=QNN_DATATYPE_UFIXED_POINT_8 rank=2 dimensions=(3 4 ) memType=QNN_TENSORMEMTYPE_RAW quantizeParams: encodingDefinition=QNN_DEFINITION_DEFINED quantizationEncoding=QNN_QUANTIZATION_ENCODING_SCALE_OFFSET scale=0.00215686 offset=-46
 node_outputs:
 name=node_token_16 id=5 version=1 type=QNN_TENSOR_TYPE_NATIVE dataFormat=0 dataType=QNN_DATATYPE_UFIXED_POINT_8 rank=2 dimensions=(2 4 ) memType=QNN_TENSORMEMTYPE_RAW quantizeParams: encodingDefinition=QNN_DEFINITION_DEFINED quantizationEncoding=QNN_QUANTIZATION_ENCODING_SCALE_OFFSET scale=0.000441176 offset=-40
 node_params:
 type=QNN_PARAMTYPE_SCALAR name=transpose_in0 value=0
 type=QNN_PARAMTYPE_SCALAR name=transpose_in1 value=0

[HectorSVC]

/azp run Linux QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows ARM64 QNN CI Pipeline,Linux Android Emulator QNN CI Pipeline

[azure-pipelines]

No pipelines are associated with this pull request.

[HectorSVC]

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 5 pipeline(s).

[HectorSVC]