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.
Summary
DistilBERT fill-mask/question-answering and BLIP image-to-text e2e regressions.
Root causes
Fixes
attention_maskdecoder_wrapperkwargs supportValidation
Focused unit tests and e2e tests passed: question-answering, fill-mask, and image-to-text-fp16.