Skip to content

webgpu: fix conv error when using MatMulNaiveProgram#24496

Merged
guschmue merged 1 commit intomicrosoft:mainfrom
xhcao:fix-conv
Apr 25, 2025
Merged

webgpu: fix conv error when using MatMulNaiveProgram#24496
guschmue merged 1 commit intomicrosoft:mainfrom
xhcao:fix-conv

Conversation

@xhcao
Copy link
Contributor

@xhcao xhcao commented Apr 22, 2025

Description

Motivation and Context

@xhcao
Copy link
Contributor Author

xhcao commented Apr 22, 2025

This PR resolves below error when running sd-turbo-ort-web/vae_decoder
[E:onnxruntime:sd-turbo-vae-hf, sequential_executor.cc:572 onnxruntime::ExecuteKernel] Non-zero status code returned while running Conv node. Name:'/post_quant_conv/Conv_token_3' Status Message: shader_helper.cc:192 onnxruntime::webgpu::`anonymous-namespace'::ValidateVariableShape Tensor original shape {4} cannot reshape to {4} with component number 4

@jchen10 PTAL

@guschmue guschmue added the ep:WebGPU ort-web webgpu provider label Apr 23, 2025
@guschmue
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).

@guschmue guschmue merged commit 1e118d6 into microsoft:main Apr 25, 2025
70 checks passed
ankitm3k pushed a commit to intel/onnxruntime that referenced this pull request May 12, 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.

5 participants