From 76f2798059575a96a12e4d34342165a4b6a6a312 Mon Sep 17 00:00:00 2001 From: Raman Shinde Date: Sat, 11 Jul 2026 13:58:29 +0530 Subject: [PATCH] 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. --- ggml/src/ggml-vulkan/ggml-vulkan.cpp | 8 ++++++++ 1 file changed, 8 insertions(+) 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;