Skip to content

Comments

[QNN EP] Fuse scale into softmax#24809

Merged
HectorSVC merged 5 commits intomicrosoft:mainfrom
CodeLinaro:dev/yuduow/scale-softmax-fusion
May 28, 2025
Merged

[QNN EP] Fuse scale into softmax#24809
HectorSVC merged 5 commits intomicrosoft:mainfrom
CodeLinaro:dev/yuduow/scale-softmax-fusion

Conversation

@qti-yuduo
Copy link
Contributor

@qti-yuduo qti-yuduo commented May 19, 2025 •
edited
Loading

QNN Softmax op defines pre-scale (beta) that we can fold constant scalar multiply into it.

@qti-yuduo
Copy link
Contributor Author

qti-yuduo commented May 19, 2025

@microsoft-github-policy-service agree [company=Qualcomm]

@qti-yuduo qti-yuduo force-pushed the dev/yuduow/scale-softmax-fusion branch from 3b33063 to 2e8583a Compare May 19, 2025 18:36
@qti-yuduo
Copy link
Contributor Author

qti-yuduo commented May 19, 2025

@microsoft-github-policy-service agree

@yuslepukhin
Copy link
Member

yuslepukhin commented May 19, 2025

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,ONNX Runtime Web CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline

@yuslepukhin
Copy link
Member

yuslepukhin commented May 19, 2025

/azp run Linux QNN CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline

@azure-pipelines
Copy link

azure-pipelines bot commented May 19, 2025

Azure Pipelines successfully started running 3 pipeline(s).

@azure-pipelines
Copy link

azure-pipelines bot commented May 19, 2025

Azure Pipelines successfully started running 4 pipeline(s).

@edgchen1 edgchen1 added the ep:QNN issues related to QNN exeution provider label May 20, 2025
@HectorSVC
Copy link
Contributor

HectorSVC commented May 20, 2025

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines
Copy link

azure-pipelines bot commented May 20, 2025

Azure Pipelines successfully started running 5 pipeline(s).

@qti-yuduo qti-yuduo force-pushed the dev/yuduow/scale-softmax-fusion branch from f1b7014 to ecbbcf7 Compare May 20, 2025 21:14
@HectorSVC
Copy link
Contributor

HectorSVC commented May 20, 2025

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines
Copy link

azure-pipelines bot commented May 20, 2025

Azure Pipelines successfully started running 5 pipeline(s).

@HectorSVC
Copy link
Contributor

HectorSVC commented May 22, 2025

You only need to check the QNN related build. You should have access to the build pipeline, so is the build log.
For Linux:
/mnt/vss/_work/_temp/bfb99205-f415-44a0-be47-77d7f5a6877e.sh: line 3: 118621 Segmentation fault (core dumped) ./build/Release/onnx_test_runner -e qnn -j 1 -i "backend_path|/mnt/vss/_work/_temp/qnn-v2.33.2.250410/lib/x86_64-linux-clang/libQnnCpu.so" cmake/external/onnx/onnx/backend/test/data/node
You can run onnx_test_runner to reproduce it.

For Windows:
1: [ FAILED ] 5 tests, listed below:
1: [ FAILED ] QnnHTPBackendTests.ScaleSoftmaxFusionScalarInitializer
1: [ FAILED ] QnnHTPBackendTests.ScaleSoftmaxFusionScalarConstant
1: [ FAILED ] QnnHTPBackendTests.ScaleSoftmaxFusionScalarInitializerReversed
1: [ FAILED ] QnnHTPBackendTests.ScaleSoftmaxFusionScalarConstantReversed
1: [ FAILED ] QnnHTPBackendTests.ScaleSoftmaxFusionSoftmaxNegativeAxis
1:
1: 5 FAILED TESTS
1: YOU HAVE 13 DISABLED TESTS
1:
1/9 Test #1: onnxruntime_test_all ....................***Failed 248.51 sec
You can run command to repro:
onnxruntime_test_all.exe --gtest_filter=QnnHTPBackendTests.ScaleSoftmaxFusionScalarInitializer

@qti-yuduo
Copy link
Contributor Author

qti-yuduo commented May 22, 2025 •
edited
Loading

@HectorSVC mind help trigger CI again? Thank you!!

@HectorSVC
Copy link
Contributor

HectorSVC commented May 22, 2025

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines
Copy link

azure-pipelines bot commented May 22, 2025

Azure Pipelines successfully started running 5 pipeline(s).

@qti-yuduo
Copy link
Contributor Author

qti-yuduo commented May 23, 2025 •
edited
Loading

I can repro the Linux error, It should be fixed now.

@qti-yuduo qti-yuduo force-pushed the dev/yuduow/scale-softmax-fusion branch from 5a40bde to 09a403d Compare May 23, 2025 20:06
@HectorSVC
Copy link
Contributor

HectorSVC commented May 23, 2025

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines
Copy link

azure-pipelines bot commented May 23, 2025

Azure Pipelines successfully started running 5 pipeline(s).

@qti-yuduo
Copy link
Contributor Author

qti-yuduo commented May 28, 2025

ping.

HectorSVC
HectorSVC approved these changes May 28, 2025
View reviewed changes
Copy link
Contributor

@HectorSVC HectorSVC left a comment

Choose a reason for hiding this comment

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

:shipit:

@HectorSVC HectorSVC merged commit f9739c2 into microsoft:main May 28, 2025
82 checks passed
@qti-yuduo qti-yuduo deleted the dev/yuduow/scale-softmax-fusion branch July 18, 2025 20:14
adrianlizarraga pushed a commit that referenced this pull request Aug 1, 2025
@qti-yuduo @adrianlizarraga
[QNN EP] Fuse scale into softmax (#24809)
255bcdd 
QNN [Softmax op defines pre-scale (`beta`)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/MasterOpDef.html#softmax) that we can fold constant scalar multiply into it.
@adrianlizarraga adrianlizarraga mentioned this pull request Aug 1, 2025
Merged
adrianlizarraga pushed a commit that referenced this pull request Aug 5, 2025
@qti-yuduo @adrianlizarraga
[QNN EP] Fuse scale into softmax (#24809)
e7e0c20 
QNN [Softmax op defines pre-scale (`beta`)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/MasterOpDef.html#softmax) that we can fold constant scalar multiply into it.
adrianlizarraga added a commit that referenced this pull request Aug 11, 2025
@adrianlizarraga @zhaoxul-qti
@1duo @HectorSVC @chenweng-quic @qti-yuduo @Akupadhye @qti-jkilpatrick @jywu-msft @github-actions @quic-calvnguy @fs-eire
rel-1.22.2 cherry-pick 1 (#25633)
19f37d7 
### Description
- #24265
- #24616
- #24640
- #24707
- #24646
- #24750
- #24809
- #24895
- #24820
- #25002
- #25171
- #25283
- #24818
- #25351
- #25361
- #25388
- #25520
- #25158




### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: quic-zhaoxul <[email protected]>
Co-authored-by: Yuduo Wu <[email protected]>
Co-authored-by: Hector Li <[email protected]>
Co-authored-by: chenweng-quic <[email protected]>
Co-authored-by: qti-yuduo <[email protected]>
Co-authored-by: Akupadhye <[email protected]>
Co-authored-by: Jeff Kilpatrick <[email protected]>
Co-authored-by: Jeff Kilpatrick <[email protected]>
Co-authored-by: George Wu <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: quic-calvnguy <[email protected]>
Co-authored-by: Changming Sun <[email protected]>
Co-authored-by: Yulong Wang <[email protected]>
This was referenced Sep 29, 2025
Closed
Closed
Closed
Merged
This was referenced Oct 13, 2025
Closed
Merged
Closed
This was referenced Oct 26, 2025
Merged
Closed
Closed
@dependabot dependabot bot mentioned this pull request Nov 17, 2025
Merged
quic-ankus pushed a commit to CodeLinaro/onnxruntime that referenced this pull request Nov 25, 2025
@qti-yuduo @qti-hungjuiw
[QNN EP] Fuse scale into softmax (microsoft#24809)
9454051 
QNN [Softmax op defines pre-scale (`beta`)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/MasterOpDef.html#softmax) that we can fold constant scalar multiply into it.
@dependabot dependabot bot mentioned this pull request Dec 8, 2025
Open
@dependabot dependabot bot mentioned this pull request Jan 17, 2026
Merged
@dependabot dependabot bot mentioned this pull request Jan 27, 2026
Closed
This was referenced Feb 9, 2026
Open
Open
This was referenced Feb 23, 2026
Open
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@yuslepukhin yuslepukhin yuslepukhin left review comments

+1 more reviewer

@HectorSVC HectorSVC HectorSVC approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

ep:QNN issues related to QNN exeution provider

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@qti-yuduo @yuslepukhin @HectorSVC @edgchen1