From 663716ce4229fe9880b4190809199730550acd16 Mon Sep 17 00:00:00 2001
From: Eve <139727413+netrunnereve@users.noreply.github.com>
Date: Sun, 15 Dec 2024 15:47:24 -0500
Subject: [PATCH] only s_warptile_mmq needs to be run with 32 threads or more

---
 ggml/src/ggml-vulkan/ggml-vulkan.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index 7267f9966..b1c5bad72 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -1442,7 +1442,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
 
         l_warptile = { 128, 128, 128, 16, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
         m_warptile = { 128,  64,  64, 16, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };
-        s_warptile = { subgroup_size_32, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
+        s_warptile = { subgroup_size_16, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
 
         l_warptile_mmq = { 128, 128, 128, 32, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
         m_warptile_mmq = { 128,  64,  64, 32, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };