Skip to content

ggml : WebGPU add TRANSPOSE and RESHAPE to supported ops #15695

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 8 commits into from
Sep 1, 2025
Merged

ggml : WebGPU add TRANSPOSE and RESHAPE to supported ops #15695

Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
522ae98
ci : disable flash attention for webgpu test
danbev Aug 31, 2025
7acee24
Revert "ci : disable flash attention for webgpu test"
danbev Aug 31, 2025
52794d3
tests : conditionally disable flash attention in webgpu
danbev Aug 31, 2025
71203bd
Revert "tests : conditionally disable flash attention in webgpu"
danbev Aug 31, 2025
ea8412f
ggml : WebGPU add TRANSPOSE and RESHAPE to supported ops
danbev Aug 31, 2025
36d632f
ggml : WebGPU added cases for TRANSPOSE and RESHAPE operations
danbev Sep 1, 2025
adeb0b5
squash! ggml : WebGPU added cases for TRANSPOSE and RESHAPE operation…
danbev Sep 1, 2025
b05a487
squash! ggml : WebGPU added cases for TRANSPOSE and RESHAPE operation…
danbev Sep 1, 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
8 changes: 8 additions & 0 deletions ggml/src/ggml-webgpu/ggml-webgpu.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -627,6 +627,12 @@ static bool ggml_webgpu_encode_node(webgpu_context ctx, ggml_tensor * node) {
ggml_webgpu_mul_mat(ctx, src0, src1, node);
break;
}
case GGML_OP_TRANSPOSE:
case GGML_OP_RESHAPE:
{
// TODO: implement these operations
break;
}
default:
return false;
}
Expand Down Expand Up @@ -1062,6 +1068,8 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
case GGML_OP_NONE:
case GGML_OP_VIEW:
case GGML_OP_PERMUTE:
case GGML_OP_TRANSPOSE:
case GGML_OP_RESHAPE:
return true;
case GGML_OP_CPY:
case GGML_OP_SET_ROWS:
Expand Down
Loading