Skip to content

LLM inference in C/C++

C++ ggml

llama : skip main_gpu validation when no devices are available (#23405)

Dev-iLb4024af6c244
diff --git a/src/llama.cpp b/src/llama.cpp
index a67fa8039a..0de6048f28 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 {