Fill DequantizeLinear CUDA opset gap (21 → 25)#27745
Closed
Conversation
…, add opset 25 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 18:15
View session
Contributor
|
/azp run Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
…nel registration Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 the existing CUDA
DequantizeLinearnon-versioned opset 21 registration to versioned 21–24, and adds a new non-versioned opset 25 registration with identical type support.quantize_linear.ccREGISTER_DQ_KERNEL_TWO_TYPED_21→REGISTER_DQ_KERNEL_TWO_TYPED_21_24(usesONNX_OPERATOR_VERSIONED_TWO_TYPED_KERNEL_EX)REGISTER_DQ_KERNEL_TWO_TYPED_25(usesONNX_OPERATOR_TWO_TYPED_KERNEL_EX)cuda_execution_provider.ccONNX_OPERATOR_TWO_TYPED_KERNEL_CLASS_NAME(..., 21, ...)toONNX_OPERATOR_VERSIONED_TWO_TYPED_KERNEL_CLASS_NAME(..., 21, 24, ...)BuildKernelCreateInfoentries added for opset 25Same type matrix across both ranges:
{uint8_t, int8_t, UInt4x2, Int4x2} × {float, MLFloat16}+ Float8 variants.Motivation and Context
CUDA
DequantizeLinearwas registered only up to opset 21; ONNX spec defines it through opset 25. Models exported at opset ≥22 would fail kernel lookup on CUDA EP.Follows the standard opset gap-filling pattern (see e.g. #27728).
Related: #27729