From b4024af6c244e355cac1a0c3368c3bca623acf1b Mon Sep 17 00:00:00 2001
From: Dev-iL <6509619+Dev-iL@users.noreply.github.com>
Date: Wed, 17 Jun 2026 17:30:26 +0300
Subject: [PATCH] llama : skip main_gpu validation when no devices are
 available (#23405)

---
 src/llama.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama.cpp b/src/llama.cpp
index a67fa8039..0de6048f2 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -249,7 +249,7 @@ static bool llama_prepare_model_devices(const llama_model_params & params, llama
     }
 
     // if using single GPU mode, remove all except the main GPU
-    if (params.split_mode == LLAMA_SPLIT_MODE_NONE) {
+    if (params.split_mode == LLAMA_SPLIT_MODE_NONE && !model->devices.empty()) {
         if (params.main_gpu < 0) {
             model->devices.clear();
         } else {