Fix e2e regressions in HF export mask handling for QNN path

[fangyangci]

Summary

DistilBERT fill-mask/question-answering and BLIP image-to-text e2e regressions.

Root causes

• SDPA attention mask dtype mismatch
• Decoder kwargs path incompatibility
• BLIP decoder mask shape mismatch

Fixes

• Export IO bool normalization for binary attention_mask
• Robust transformers compatibility patching
• decoder_wrapper kwargs support
• BLIP 2D mask pass-through

Validation

Focused unit tests and e2e tests passed: question-answering, fill-mask, and image-to-text-fp16.

[xieofxie]

dup of #1385 ?