Update Flatten CUDA operator to fill opset gap (13 → 25)#27736
Closed
Update Flatten CUDA operator to fill opset gap (13 → 25)#27736
Conversation
Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
tianleiwu
March 18, 2026 17:53
View session
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Extends CUDA
Flattenkernel registration from opset 13 through opset 25, following the same pattern used for other operators (ConstantOfShape, Identity, If, Loop, Scan, Size) in #27728.flatten.cc: Split single opset-13 registration into versioned ranges 13–20, 21–22, 23–24, and final 25cuda_execution_provider.cc: Added corresponding forward declarations and function table entries for each new opset rangeNo logic or type constraint changes — Flatten is a pure reshape, so the kernel implementation is identical across all opset versions.
Motivation and Context
CUDA
Flattenwas registered only at opset 13 while ONNX defines it through opset 25 (a 12-opset gap). This causes models exported at newer opsets to fall back from the CUDA EP. See #27729.