Fix float16 trunc division rounding - #3025
Open
αI (Alphaxiaoteng) wants to merge 1 commit into
Open
Conversation
|
αI (@Alphaxiaoteng) please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #990.
ONNX Runtime can evaluate the float16 division in
aten::div(..., rounding_mode="trunc")with a higher-precision intermediate than PyTorch. Applying truncation to that value can produce an off-by-one result at float16 boundaries.Materialize the float16 quotient before truncation, matching PyTorch's float16 rounding semantics. The existing float16
trunc_roundingregression case is enabled again.Tests
python -m pytest tests/function_libs/torch_lib/ops_test.py -k test_output_match_opinfo__div_mode -vvruff check onnxscript/function_libs/torch_lib/ops/core.py tests/function_libs/torch_lib/ops_test_data.pyruff format --check onnxscript/function_libs/torch_lib/ops/core.py tests/function_libs/torch_lib/ops_test_data.pygit diff --check