llama : fix unused warning

diff --git a/llama.cpp b/llama.cpp
index 73b932a74eea3f19f677cc47a6961e7b5c1ee375..98f49abd7cf4839df53bad2fa63bba98c8241a21 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -1053,6 +1053,8 @@ static void llama_model_load_internal(
 
         fprintf(stderr, "%s: [cublas] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
     }
+#else
+    (void) n_gpu_layers;
 #endif
 
     // loading time will be recalculate after the first eval, so