From 73f94ff366fd0800c8f954166e6a4cf7973e0991 Mon Sep 17 00:00:00 2001
From: Gong-Mi <550230171@qq.com>
Date: Tue, 20 Jan 2026 21:30:32 +0800
Subject: [PATCH] ggml-vulkan: Refine mobile tuning (optimize ARM & disable
 unstable Qualcomm configs)

- Android Baseline: Adjusted configurations to avoid large tile allocations, establishing a stable performance floor for mobile devices.
- ARM Optimization: Clarified and explicitly restored optimized warptile tuning for ARM architectures.
- Qualcomm Stability Fix: Removed Qualcomm-specific tuning as Adreno drivers frequently trigger fatal timeouts/crashes. Deprecating support for large models (>1B) on Qualcomm via Vulkan for now.
---
 ggml/src/ggml-vulkan/ggml-vulkan.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 116009a13a..00f8a42eb8 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -3037,6 +3037,11 @@ static void ggml_vk_load_shaders(vk_device& device) {
             // Xe2/Xe3 with coopmat enabled - warptile performance tuning
             l_warptile = { 512, 128, 128, 16, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
             l_warptile_mmq = { 512, 128, 128, 32, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
+        } else if (device->vendor_id == VK_VENDOR_ID_ARM && device->subgroup_size >= 16) {
+            uint32_t wm = 32 / device->subgroup_size;
+            m_warptile_mmq = m_warptile_mmq_int = { 64, 64, 64, 16, 16, 32, wm, 2, 2, 1, device->subgroup_size };
+            m_warptile = { 64, 64, 64, 16, 16, 32, wm, 2, 2, 1, device->subgroup_size };
+            m_warptile_id = m_warptile_mmqid = { 64, 64, 64, 16, 16, 32, wm, 2, 2, 1, device->subgroup_size };
         }
 
         l_mmq_wg_denoms = l_wg_denoms = {128, 128, 1 };