happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

vulkan: workaround MoltenVK compile failure in multi_add (#15506) 

* vulkan: workaround MoltenVK compile failure in multi_add

* Update ggml/src/ggml-vulkan/vulkan-shaders/multi_add.comp

Co-authored-by: 0cc4m <picard12@live.de>
This commit is contained in:
Jeff Bolz 2025-08-24 03:48:21 -05:00 committed by GitHub
parent 710dfc465a
commit e78cf0d4b1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-vulkan/vulkan-shaders/multi_add.comp
View File

@ -23,8 +23,11 @@ layout (push_constant) uniform parameter2
uint rms_partials;
} p;
layout (binding = 0) readonly buffer A {A_TYPE data_a[];} a[];
layout (binding = 0) writeonly buffer D {D_TYPE data_d[];} d[];
// Workaround for MoltenVK Bug, see https://github.com/ggml-org/llama.cpp/issues/15498
// layout (binding = 0) readonly buffer A {A_TYPE data_a[];} a[];
// layout (binding = 0) writeonly buffer D {D_TYPE data_d[];} d[];
layout (binding = 0) buffer A {A_TYPE data_a[];} a[];
layout (binding = 0) buffer D {D_TYPE data_d[];} d[];
layout (binding = 0, std430) buffer PartialBuf {float partial_sums[];} partials[];