Skip to content

LLM inference in C/C++

C++ ggml

Vulkan: route large matmuls to medium tile on Adreno (#24877)

Raman Shinde76f279805957
diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index a483d22c1a..1134a3bbd9 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -6501,6 +6501,14 @@ static vk_device ggml_vk_get_device(size_t idx) {
device->mul_mat_id_m[i] = true;
device->mul_mat_id_s[i] = false;
break;
+ case VK_VENDOR_ID_QUALCOMM:
+ device->mul_mat_l[i] = false;
+ device->mul_mat_m[i] = true;
+ device->mul_mat_s[i] = true;
+ device->mul_mat_id_l[i] = false;
+ device->mul_mat_id_m[i] = true;
+ device->mul_mat_id_s[i] = true;
+ break;
#endif
default:
device->mul_mat_l[i] = true;