onnxruntime

a25d0d29 - Add --mask_type option to generate different format of attention mask in bert_perf_test.py (#16976)

Add --mask_type option to generate different format of attention mask in bert_perf_test.py (#16976) ### Description Add an option to generate different formats of attention_mask for testing transformers models: 1 - 1D mask index, actual sequence length excluding padding 2 - 2D attention mask. Value 0 means padding, 1 otherwise. 3 - 1D, key lengths and cumulated sequence lengths of query and key ### 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. -->