diff --git a/ggml-cuda/fattn-tile-f32.cu b/ggml-cuda/fattn-tile-f32.cu
index 54db765e2..b8b2f69e1 100644
--- a/ggml-cuda/fattn-tile-f32.cu
+++ b/ggml-cuda/fattn-tile-f32.cu
@@ -283,8 +283,7 @@ void launch_fattn_tile_f32_64_128(ggml_backend_cuda_context & ctx, ggml_tensor *
 }
 
 void ggml_cuda_flash_attn_ext_tile_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
-    const ggml_tensor * KQV = dst;
-    const ggml_tensor * Q   = dst->src[0];
+    const ggml_tensor * Q = dst->src[0];
 
     if (Q->ne[1] <= 16) {
         constexpr int cols_per_block = 16;