[Relax][ONNX] Support exclusive option in CumSum#19773
Merged
tlopex merged 1 commit intoJun 15, 2026
Merged
Conversation
The CumSum converter aborted on any node with exclusive=1 via a bare assert. relax.op.cumsum and topi.cumsum already implement the exclusive form, so pass the attribute through instead of rejecting it. The existing flip-cumsum-flip reverse handling composes correctly with exclusive. Extend test_cumsum to cover exclusive=True so check_correctness exercises all four reverse/exclusive combinations against ONNX Runtime. Fixes apache#19692
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request adds support for the exclusive attribute in the ONNX CumSum operator converter within the Relax frontend. It updates the CumSum implementation to extract and pass the exclusive flag to the underlying relax.op.cumsum operation, and expands the test suite to cover both True and False values for this parameter. There are no review comments, and I have no feedback to provide.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
tlopex
approved these changes
Jun 15, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Root Cause
The ONNX
CumSumconverter in the Relax frontend rejected any node withexclusive=1via a bareassert not attr.get("exclusive", False), "Exclusive option not yet supported.", so importing amodel that used exclusive cumulative sums failed with
AssertionError: Exclusive option not yet supported.. The underlying op already supports the exclusive form:relax.op.cumsumforwards anexclusiveflag to the FFI andtopi/scan.pyimplements the exclusive branch, so the converteronly needed to pass the attribute through.
Solution
Drop the assert and read the attribute as
exclusive = attr.get("exclusive", 0) != 0(matching theexisting
attr.get("reverse", 0) != 0idiom in the same converter), then pass it torelax.op.cumsum(data, axis, exclusive=exclusive). The existing reverse handling(
flip -> cumsum -> flip) composes correctly with exclusive, soreverse=1, exclusive=1lowers toan exclusive scan over the reversed axis.
Test Plan
Extended
test_cumsumintests/python/relax/test_frontend_onnx.pyto parametrizeexclusiveover[True, False], socheck_correctnessnow exercises all four(reverse, exclusive)combinationsagainst ONNX Runtime:
Issue
Fixes #19692