From 19836568c4f1b504d8ee579b7ab7fcf4edbd8f78 Mon Sep 17 00:00:00 2001
From: Gabriel <wyzixg@yahoo.com>
Date: Fri, 18 Sep 2026 20:33:25 +0300
Subject: [PATCH] cuda: avoid short-query MMA FA crash with quantized V

---
 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 ab7a3b297c07..b6ef1f141c29 100644
--- a/ggml/src/ggml-cuda/fattn.cu
+++ b/ggml/src/ggml-cuda/fattn.cu
@@ -9,6 +9,12 @@ template <int DKQ, int DV, int ncols2>
 static void ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
     const int cc = ggml_cuda_info().devices[ggml_cuda_get_device()].cc;
     const ggml_tensor * Q = dst->src[0];
+    const ggml_tensor * V = dst->src[2];
+
+    if (turing_mma_available(cc) && ggml_is_quantized(V->type) && Q->ne[1] > 2 && Q->ne[1] <= 4) {
+        ggml_cuda_flash_attn_ext_mma_f16_case<DKQ, DV, 64/ncols2, ncols2>(ctx, dst);
+        return;
+    }
 
     if constexpr (ncols2 <= 8) {
         if (turing_mma_available(cc) && Q->ne[1] <= 8/ncols2) {