Skip to content

webgpu: route up to 8 columns through the mat-vec kernel #301

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
bri-prism merged 1 commit into from
Oct 2, 2026
+3 −1
Merged

webgpu: route up to 8 columns through the mat-vec kernel #301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions ggml/src/ggml-webgpu/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,3 +81,5 @@ endif()

target_include_directories(ggml-webgpu PRIVATE ${SHADER_OUTPUT_DIR})
target_link_libraries(ggml-webgpu PRIVATE ${DawnWebGPU_TARGET})

target_compile_features(ggml-webgpu PRIVATE cxx_std_20)
2 changes: 1 addition & 1 deletion ggml/src/ggml-webgpu/ggml-webgpu.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1603,7 +1603,7 @@ static webgpu_encoded_op ggml_webgpu_mul_mat(webgpu_context & ctx,
ggml_tensor * src1,
ggml_tensor * dst) {
// Determine if this is a mat-vec operation
bool use_mat_vec = (dst->ne[1] <= 4);
bool use_mat_vec = (dst->ne[1] <= 8);

// use MMVQ path for mat-vec
bool use_mmvq = ggml_webgpu_can_use_mmvq(src0, src1, ctx->global_ctx->capabilities.supports_dot_product,
Expand Down
Loading