onnxruntime

ec0e4d3b - Parallel Transpose_BSNH_to_BNSH (#19406)

Parallel Transpose_BSNH_to_BNSH (#19406) Achieved a speedup of 1.098 in MultiHeadAttention and an end-to-end speedup of 1.021 in the OCR model through parallelization of the Transpose_BSNH_to_BNSH operation.