From ca99f79ea961290c982583f61b61fd01bc566086 Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Fri, 6 Jun 2025 13:57:00 +0800
Subject: [PATCH] cu11 just always stick to wmma

---
 ggml/src/ggml-cuda/fattn.cu | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ggml/src/ggml-cuda/fattn.cu b/ggml/src/ggml-cuda/fattn.cu
index b809329b8..22834c03b 100644
--- a/ggml/src/ggml-cuda/fattn.cu
+++ b/ggml/src/ggml-cuda/fattn.cu
@@ -342,7 +342,7 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
     }
 
     // The MMA implementation needs Turing or newer, use the old WMMA code for Volta:
-    if (cc == GGML_CUDA_CC_TURING || (fp16_mma_available(cc) && !new_mma_available(cc))) { //kcpp: turing use wmma to fix cu11 incoherence
+    if (ggml_cuda_highest_compiled_arch(cc) <= GGML_CUDA_CC_TURING || cc == GGML_CUDA_CC_TURING || (fp16_mma_available(cc) && !new_mma_available(cc))) { //kcpp: use wmma to fix cu11 incoherence
         ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);
         return;
     }