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

* [Vulkan] Fixes llama-cli breaking over longer promts sizes

The llama-cli was breaking for longer promts sizes for q4_0 quantized networks. Causing due to insufficient shared memory.

* Removed the un-used Adreno device

* Updated matmul for small pipeline.

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index a483d22c1a26a8b0118a3b33e70d54b4eea6a7a4..1134a3bbd90c10121796641e87abb54d3392d53e 100644 (file)
--- 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;