Skip to content

Comments

Attention Operator (CPU)#25156

Merged
xadupre merged 56 commits intomainfrom
xadupre/attention
Jul 25, 2025
Merged

Attention Operator (CPU)#25156
xadupre merged 56 commits intomainfrom
xadupre/attention

Conversation

@xadupre
Copy link
Member

@xadupre xadupre commented Jun 24, 2025

Description

Implementation Attention(23) for CPU.

The backend tests from onnx were wrong for Attention (see onnx/onnx#7142). The onnx version needs to be updated to make all tests pass. The implementation matches the reference implementation after onnx was fixed.

Copy link
Contributor

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can commit the suggested changes from lintrunner.

@titaiwangms titaiwangms self-requested a review June 30, 2025 21:52
@xadupre xadupre changed the title [DRAFT] Attention Operator (CPU) Attention Operator (CPU) Jul 8, 2025
@xadupre xadupre marked this pull request as ready for review July 8, 2025 10:38
@titaiwangms titaiwangms requested a review from tianleiwu July 8, 2025 17:26
justinchuby
justinchuby previously approved these changes Jul 22, 2025
@titaiwangms titaiwangms self-assigned this Jul 24, 2025
@xadupre xadupre merged commit c3499d7 into main Jul 25, 2025
92 of 95 checks passed
@xadupre xadupre deleted the xadupre/attention branch July 25, 2025 12:58
@snnn
Copy link
Contributor

snnn commented Jul 25, 2025

Hi there! We haven't cut the release branch for this version yet, so I'm removing the release:1.23.0 label for now to keep things tidy. Thanks so much for your contribution! We'll make sure this gets included when the release is prepared. 🤖

RyanMetcalfeInt8 pushed a commit to RyanMetcalfeInt8/onnxruntime that referenced this pull request Jul 29, 2025
### Description
Implementation Attention(23) for CPU.

The backend tests from onnx were wrong for Attention (see
onnx/onnx#7142). The onnx version needs to be
updated to make all tests pass. The implementation matches the reference
implementation after onnx was fixed.

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ti-Tai Wang <[email protected]>
Co-authored-by: kunal-vaishnavi <[email protected]>
sanketkaleoss pushed a commit to sanketkaleoss/onnxruntime that referenced this pull request Aug 11, 2025
### Description
Implementation Attention(23) for CPU.

The backend tests from onnx were wrong for Attention (see
onnx/onnx#7142). The onnx version needs to be
updated to make all tests pass. The implementation matches the reference
implementation after onnx was fixed.

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ti-Tai Wang <[email protected]>
Co-authored-by: kunal-vaishnavi <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

7 participants