microsoft / microsoft/winml-cli

Fix e2e regressions in HF export mask handling for QNN path

Open
#1,385 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
40
Forks
11
Avg merge
1d 8h
Merged PRs (30d)
50

Description

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 compat patching
  • decoder_wrapper kwargs support
  • BLIP 2D mask pass-through

Validation

  • focused unit tests passed
  • e2e passed: question-answering, fill-mask, image-to-text-fp16

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by running the focused unit tests mentioned in the issue, then reproduce the three named e2e cases: question-answering, fill-mask, and image-to-text-fp16. Trace the export IO bool normalization, transformers compatibility patching, decoder_wrapper kwargs handling, and BLIP 2D mask pass-through; done means the focused tests and all three e2e cases pass.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, testing-qa
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.