KEMBAR78
[QNN EP] Fuse scale into softmax by qti-yuduo · Pull Request #24809 · microsoft/onnxruntime · GitHub
Skip to content

[QNN EP] Fuse scale into softmax #24809

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 5 commits into from
May 28, 2025
Merged

[QNN EP] Fuse scale into softmax #24809

merged 5 commits into from
May 28, 2025

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

@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

@microsoft-github-policy-service agree

@yuslepukhin
Copy link
Member

/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

/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 successfully started running 3 pipeline(s).

@azure-pipelines
Copy link

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

/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 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

/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 successfully started running 5 pipeline(s).

@HectorSVC
Copy link
Contributor

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

/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 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

/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 successfully started running 5 pipeline(s).

@qti-yuduo
Copy link
Contributor Author

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 @jeffkilpatrick @jywu-msft @github-actions @quic-calvnguy @snnn @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 <quic_zhaoxul@quicinc.com>
Co-authored-by: Yuduo Wu <6426433+1duo@users.noreply.github.com>
Co-authored-by: Hector Li <hecli@microsoft.com>
Co-authored-by: chenweng-quic <168707118+chenweng-quic@users.noreply.github.com>
Co-authored-by: qti-yuduo <yuduow@qti.qualcomm.com>
Co-authored-by: Akupadhye <aupadhye@qti.qualcomm.com>
Co-authored-by: Jeff Kilpatrick <jkilpatrick@qti.qualcomm.com>
Co-authored-by: Jeff Kilpatrick <jkilpat@qti.qualcomm.com>
Co-authored-by: George Wu <jywu@microsoft.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: quic-calvnguy <quic_calvnguy@quicinc.com>
Co-authored-by: Changming Sun <chasun@microsoft.com>
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
This was referenced Sep 29, 2025
Closed
Closed
Closed
Merged
This was referenced Oct 13, 2025
Open
Merged
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

@HectorSVC HectorSVC HectorSVC approved these changes

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