Skip to content

Bug fix for conv1d #26421

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

Merged
merged 2 commits into from
Oct 29, 2025
Merged

Bug fix for conv1d #26421

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a042076
bug fix for conv1d
wenqinI Oct 28, 2025
5832052
only adjusted the dispatch size when rank is 4
wenqinI Oct 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions onnxruntime/core/providers/webgpu/tensor/transpose.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,10 +168,12 @@ Status Transpose::DoTranspose(onnxruntime::webgpu::ComputeContext& context,
//
// TODO: Revert this change once the driver issue is fixed.
if (context.AdapterInfo().vendor == std::string_view{"intel"}) {
ORT_ENFORCE(rank == static_cast<size_t>(4), "Input tensor must have rank 4.");
dispatch_x = ceil_div(input_shape[0] * input_shape[1], 2);
dispatch_y = ceil_div(input_shape[2], 4);
dispatch_z = ceil_div(input_shape[3], 8);
// Only adjusted the dispatch size when rank is 4 yet.
if (rank == static_cast<size_t>(4)) {
dispatch_x = ceil_div(input_shape[0] * input_shape[1], 2);
dispatch_y = ceil_div(input_shape[2], 4);
dispatch_z = ceil_div(input_shape[3], 8);
}
}
program.SetDispatchGroupSize(dispatch_x, dispatch_y, dispatch_z);
}
Expand Down
Loading