From: Raman Shinde <redacted>
Date: Sat, 11 Jul 2026 08:28:29 +0000 (+0530)
Subject: Vulkan: route large matmuls to medium tile on Adreno (#24877)
X-Git-Tag: upstream/0.0.10438~469
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=76f2798059575a96a12e4d34342165a4b6a6a312;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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 a483d22c1..1134a3bbd 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;