llama.cpp

e78cf0d4 - vulkan: workaround MoltenVK compile failure in multi_add (#15506)

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>