From c7bda030e7faee594dbe7550185e857351ad405d Mon Sep 17 00:00:00 2001
From: Nathan Wilson <67372905+Nathanw1014@users.noreply.github.com>
Date: Thu, 3 Sep 2026 15:40:34 +0700
Subject: [PATCH] vulkan: fix FA dequant path engagement (#28190)

Skip the nb[3] check when ne[3] == 1, the shader never reads it for a
single stream. Cache views carry the full-buffer stride there, so the old
check reduced to n_kv == kv_size and the path only engaged with the
cache full.
---
 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 285cd65253..a04a6b27a8 100644
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -10966,7 +10966,7 @@ static void ggml_vk_flash_attn(ggml_backend_vk_context * ctx, vk_context& subctx
         return t->nb[0] == ggml_type_size(t->type) &&
                t->nb[2] == ggml_row_size(t->type, t->ne[0]) &&
                t->nb[1] == t->nb[2] * t->ne[2] &&
-               t->nb[3] == t->nb[1] * t->ne[1];
+               (t->ne[3] == 1 || t->nb[3] == t->nb[1] * t->ne[1]);
     };
     const bool k_quant = k->type != GGML_TYPE_F16 && k->type != GGML_TYPE_BF16 && k->type != GGML_TYPE_F32;
     const bool v_quant = v->type != GGML_TYPE_F16 && v->type != GGML_TYPE_BF16 && v->type != GGML_TYPE_F32;