cuda : print less debug logs when disabling cuda graphs (llama/18868)

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index 553623fbd42fb4458a98eb82c6d3336037305578..ed1021469a7b058f0c9b5166ec58ccef23fecff6 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -3730,8 +3730,10 @@ static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx) {
 
     if (cuda_ctx->cuda_graph->graph == nullptr) {
         if (ggml_cuda_info().devices[cuda_ctx->device].cc < GGML_CUDA_CC_AMPERE) {
+            if (!cuda_ctx->cuda_graph->disable_due_to_gpu_arch) {
+                GGML_LOG_DEBUG("%s: disabling CUDA graphs due to GPU architecture\n", __func__);
+            }
             cuda_ctx->cuda_graph->disable_due_to_gpu_arch = true;
-            GGML_LOG_DEBUG("%s: disabling CUDA graphs due to GPU architecture\n", __func__);
         }
     }