From 74c6daba1ae983945f2ea6bf5710028b0a0e9b3d Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Fri, 15 May 2026 22:47:24 +0800
Subject: [PATCH] fix bad merge

---
 ggml/src/ggml-cuda/fattn.cu | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/ggml/src/ggml-cuda/fattn.cu b/ggml/src/ggml-cuda/fattn.cu
index 49485582a..657159368 100644
--- a/ggml/src/ggml-cuda/fattn.cu
+++ b/ggml/src/ggml-cuda/fattn.cu
@@ -479,6 +479,12 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
         return BEST_FATTN_KERNEL_MMA_F16;
     }
 
+    const int ncols2_max = Q->ne[0] == 320 ? 32 : ((Q->ne[0] == 576 || Q->ne[0] == 192) ? 16 : 8);
+    int gqa_ratio_eff = 1;
+    while (gqa_ratio % (2*gqa_ratio_eff) == 0 && gqa_ratio_eff < ncols2_max) {
+        gqa_ratio_eff *= 2;
+    }
+
     // Use the WMMA kernel if possible but only for HIP
 #if defined(GGML_HIP_ROCWMMA_FATTN)
     if (ggml_cuda_should_use_wmma_fattn(cc) && K->ne[1] % FATTN_KQ_STRIDE == 0 && Q->ne[0] != 40 && Q->ne[0] != 72 && Q->ne[0] != 192 && Q->ne[0] != 512 && Q->ne[0] != 576) {