Skip to content

[webgpu] support GatherND operator - #25632

Merged
Guenther Schmuelling (guschmue) merged 10 commits into
microsoft:mainfrom
xhcao:grather_nd
Aug 11, 2025
Merged

Guenther Schmuelling (guschmue) merged 10 commits into
microsoft:mainfrom
xhcao:grather_nd

Conversation

@xhcao

@xhcao xhcao commented Aug 1, 2025

Copy link
Copy Markdown
Contributor

Description

Motivation and Context

@xhcao

xhcao commented Aug 1, 2025

Copy link
Copy Markdown
Contributor Author

Jie Chen (@jchen10) PTAL, thanks

@jywu-mysoft George Wu (jywu-mysoft) added the ep:WebGPU ort-web webgpu provider label Aug 2, 2025
@xhcao

xhcao commented Aug 4, 2025

Copy link
Copy Markdown
Contributor Author

Guenther Schmuelling (@guschmue) Yulong Wang (@fs-eire) Please help trigger the bots, thanks.

@fs-eire

Copy link
Copy Markdown
Contributor

this need to be fixed:

/mnt/vss/_work/onnxruntime/onnxruntime/onnxruntime/core/providers/webgpu/tensor/gather_nd.cc:92:61: error: implicit conversion loses integer precision: 'int64_t' (aka 'long long') to 'difference_type' (aka 'long') [-Werror,-Wshorten-64-to-32]
   92 |   shape.insert(shape.end(), input_shape.GetDims().begin() + last_indices_dimension, input_shape.GetDims().end());
      |                                                           ~ ^~~~~~~~~~~~~~~~~~~~~~
``

@guschmue

Copy link
Copy Markdown
Contributor

CI fails on missing cast:
onnxruntime/core/providers/webgpu/tensor/gather_nd.cc:92:61: error: implicit conversion loses integer precision: 'int64_t' (aka 'long long') to 'difference_type' (aka 'long') [-Werror,-Wshorten-64-to-32]
92 | shape.insert(shape.end(), input_shape.GetDims().begin() + last_indices_dimension, input_shape.GetDims().end());

@xhcao

xhcao commented Aug 5, 2025

Copy link
Copy Markdown
Contributor Author

Done, thanks.

@fs-eire

Copy link
Copy Markdown
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
Copy Markdown
Azure Pipelines successfully started running 5 pipeline(s).

@fs-eire

Copy link
Copy Markdown
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
Copy Markdown
Azure Pipelines successfully started running 5 pipeline(s).

@guschmue
Guenther Schmuelling (guschmue) merged commit 08e18b2 into microsoft:main Aug 11, 2025
Maximilian Müller (gedoensmax) pushed a commit to gedoensmax/onnxruntime that referenced this pull request Sep 2, 2025
### Description
<!-- Describe your changes. -->



### 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. -->
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ep:WebGPU ort-web webgpu provider

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants