From 5a5aeb1e91009c72bf816400b758bb8a305616d7 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sat, 13 May 2023 16:55:14 +0300
Subject: [PATCH] llama : fix unused warning

---
 llama.cpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/llama.cpp b/llama.cpp
index 73b932a74..98f49abd7 100644
--- 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