microsoft / onnxscript

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.
https://onnxscript.ai/
MIT License
271 stars 53 forks source link

Add unit test to investigate torch issues (scaled_dot_product_attention, index_put) #1864

Open xadupre opened 2 weeks ago

xadupre commented 2 weeks ago

See https://github.com/pytorch/pytorch/issues/135615, https://github.com/pytorch/pytorch/issues/135233.

codecov[bot] commented 2 weeks ago

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 75.32%. Comparing base (a99e443) to head (2c3179f).

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #1864 +/- ## ========================================== + Coverage 75.26% 75.32% +0.06% ========================================== Files 251 251 Lines 27446 27446 Branches 5032 5032 ========================================== + Hits 20656 20673 +17 + Misses 5822 5808 -14 + Partials 968 965 -3 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

justinchuby commented 2 weeks ago

Do you have plans to merge or is this for investigation only? Marking as draft for now

justinchuby commented 2 weeks ago

We do need to rewrite our index put implementation. #1749

xadupre commented 2 weeks ago

I don't have time to implement a fix this week but anybody doing it should check the with unit tests I made and decide whether or not they should be kept.