CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* ggml : WebGPU add TRANSPOSE and RESHAPE to supported ops

This commit adds support for the TRANSPOSE and RESHAPE operations in the
ggml webgpu backend.

Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Daniel Bevenius
2025-09-01 14:28:49 +02:00
committed by GitHub
parent 4795c91c32
commit 77dee9de97
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-webgpu/ggml-webgpu.cpp
View File

@@ -611,6 +611,8 @@ static bool ggml_webgpu_encode_node(webgpu_context ctx, ggml_tensor * node) {
case GGML_OP_NONE:
case GGML_OP_VIEW:
case GGML_OP_PERMUTE:
case GGML_OP_TRANSPOSE:
case GGML_OP_RESHAPE:
return false;
case GGML_OP_CPY:
{
@@ -1062,6 +1064,8 @@ 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: