Skip to content

[WebNN] Support SkipSimplifiedLayerNormalization op - #23151

Merged
Dwayne Robinson (fdwr) merged 3 commits into
microsoft:mainfrom
Honry:skip-simplified-layernorm
Dec 24, 2024
Merged

Dwayne Robinson (fdwr) merged 3 commits into
microsoft:mainfrom
Honry:skip-simplified-layernorm

Conversation

@Honry

Copy link
Copy Markdown
Contributor

The algorithm of SkipSimplifiedLayerNormalization is quite similar to the SimplifiedLayerNormalization, only different is SkipSimplifiedLayerNormalization provides an additional output used for calculating the sum of the input, skip and bias (if it exits).

BTW, fix a bug in SimplifiedLayerNormalization, adding bias if it exits.

@Honry

Copy link
Copy Markdown
Contributor Author

The algorithm of SkipSimplifiedLayerNormalization is quite
similar to the SimplifiedLayerNormalization, only different
is SkipSimplifiedLayerNormalization provides an additional
output used for caculating the sum of the input, skip and
bias (if it exits).

BTW, fix a bug in SimplifiedLayerNormalization, adding bias
if it exits.
@guschmue Guenther Schmuelling (guschmue) added the ep:WebNN WebNN execution provider label Dec 19, 2024
@guschmue

Copy link
Copy Markdown
Contributor

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline

@guschmue

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@guschmue

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models

@guschmue

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 4 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 3 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@fdwr Dwayne Robinson (fdwr) left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

👍

Comment thread onnxruntime/core/providers/webnn/builders/impl/normalization_op_builder.cc Outdated
Comment thread onnxruntime/core/providers/webnn/builders/impl/normalization_op_builder.cc Outdated
@fdwr

Dwayne Robinson (fdwr) commented Dec 19, 2024

Copy link
Copy Markdown
Contributor

ONNX Runtime Web CI Pipeline ...
npm error code E409
npm error 409 Conflict - GET https://registry.npmjs.org/shiki/-/shiki-0.14.7.tgz
source

Possible infrastructure issue. Restarting.

Passed now.

@Honry

Copy link
Copy Markdown
Contributor Author

Dwayne Robinson (@fdwr), thanks for your comments, fixed in new commit, PTAL again.

Comment thread js/web/docs/webnn-operators.md

@fdwr Dwayne Robinson (fdwr) left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM except for the markdown change. 🤔

@fdwr

Copy link
Copy Markdown
Contributor

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline

@fdwr

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline

@fdwr

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline

@fdwr

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 3 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 4 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@fdwr

Copy link
Copy Markdown
Contributor

/azp run Python format, orttraining-linux-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

1 similar comment
@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

@fdwr Dwayne Robinson (fdwr) left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

👍 (if current models use "" or "ai.onnx" in their node domain)

@fdwr
Dwayne Robinson (fdwr) merged commit 2d05c4b into microsoft:main Dec 24, 2024
Tarek Ziade (tarekziade) pushed a commit to tarekziade/onnxruntime that referenced this pull request Jan 10, 2025
The algorithm of `SkipSimplifiedLayerNormalization` is quite similar to
the `SimplifiedLayerNormalization`, only different is
`SkipSimplifiedLayerNormalization` provides an additional output used
for calculating the sum of the input, skip and bias (if it exits).

BTW, fix a bug in `SimplifiedLayerNormalization`, adding bias if it
exits.
Guenther Schmuelling (guschmue) pushed a commit that referenced this pull request Jan 12, 2025
The algorithm of `SkipSimplifiedLayerNormalization` is quite similar to
the `SimplifiedLayerNormalization`, only different is
`SkipSimplifiedLayerNormalization` provides an additional output used
for calculating the sum of the input, skip and bias (if it exits).

BTW, fix a bug in `SimplifiedLayerNormalization`, adding bias if it
exits.
Ashrit Shetty (ashrit-ms) pushed a commit that referenced this pull request Mar 17, 2025
The algorithm of `SkipSimplifiedLayerNormalization` is quite similar to
the `SimplifiedLayerNormalization`, only different is
`SkipSimplifiedLayerNormalization` provides an additional output used
for calculating the sum of the input, skip and bias (if it exits).

BTW, fix a bug in `SimplifiedLayerNormalization`, adding bias if it
exits.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ep:WebNN WebNN execution provider

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants