onnxruntime/tools
Tianlei Wu 55f0559e5d
Update attention fusion to support SDPA pattern (#22629)
### Description
Match new SDPA pattern for huggingface BERT model that exported from
latest transformers package.

Some changes of transformers tests in CI pipeline:
(1) Enable tests for bert, distilbert and roberta models in CI.
(2) Remove out-of-date tests for huggingface models that were marked as
slow and not enabled in CI pipeline.
(3) Upgrade transformers package version to the latest.

### Motivation and Context

Recent huggingface transformers use torch SDPA in bert modeling. The
graph pattern change causes attention fusion not working anymore. Update
the fusion script to match the new pattern.
2024-11-21 09:42:41 -08:00
..
android_custom_build Update all JDK version to 17 (#22786) 2024-11-12 11:42:18 -08:00
ci_build Update attention fusion to support SDPA pattern (#22629) 2024-11-21 09:42:41 -08:00
doc Update ruff and clang-format versions (#21479) 2024-07-24 11:50:11 -07:00
nuget Cleanup code (#22827) 2024-11-19 14:13:33 -08:00
perf_view
python Add Android QNN Browserstack test (#22434) 2024-11-10 16:10:29 -08:00
scripts Cleanup code (#22827) 2024-11-19 14:13:33 -08:00