Skip to content

LLM inference in C/C++

C++ ggml

llama: only use one iGPU device by default (#23897)

Ruben Ortlam22cadc1944f4
diff --git a/src/llama.cpp b/src/llama.cpp
index edacd1d5f4..a67fa8039a 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -225,7 +225,9 @@ static bool llama_prepare_model_devices(const llama_model_params & params, llama
}
case GGML_BACKEND_DEVICE_TYPE_IGPU:
- igpus.push_back({false, dev});
+ if (igpus.empty()) {
+ igpus.push_back({false, dev});
+ }
break;
case GGML_BACKEND_DEVICE_TYPE_META:
GGML_ABORT("fatal error");