Fill CUDA EP opset gaps for Round and Equal operators#27754
Merged
Conversation
Round: version 11 → versioned 11-21 + new opset 22 Equal: version 13 → versioned 13-18 + new opset 19 Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
tianleiwu
March 19, 2026 00:04
View session
justinchuby
approved these changes
May 6, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Caps existing non-versioned CUDA kernel registrations and adds new registrations at the latest ONNX opset:
Changes across three files:
unary_elementwise_ops.cc—UNARY_OP_HFD(Round, 11)→UNARY_OP_VERSIONED_HFD+UNARY_OP_HFDbinary_elementwise_ops.cc—BINARY_LOGICALOP_REGISTER_UZILHFD(Equal, 13)→ versioned 13–18 + new 19 (same forbooltyped registration)cuda_execution_provider.cc— corresponding forward declarations andBuildKernelCreateInfoentriesNo type changes; both operators retain their existing CUDA type support at the new opsets.
Motivation and Context
Tracks with the ongoing effort to close ONNX opset coverage gaps in the CUDA execution provider (#27729). Without these registrations, models targeting opset 19+ (Equal) or 22+ (Round) fall back from CUDA to CPU.