LLM inference in C/C++
C++ ggml
llama : do not skip iGPU when only RPC devices are present (#23868)
Radoslav Gerganov1738129bee5c
diff --git a/src/llama.cpp b/src/llama.cppindex dfe30ce8f6..edacd1d5f4 100644--- a/src/llama.cpp+++ b/src/llama.cpp@@ -239,8 +239,9 @@ static bool llama_prepare_model_devices(const llama_model_params & params, llama// add GPUsmodel->devices.insert(model->devices.end(), gpus.begin(), gpus.end());- // add integrated GPUs only if no other devices were found- if (model->devices.empty()) {+ // add integrated GPUs only if no discrete GPUs were found+ // (RPC servers do not count, otherwise the local iGPU would be dropped on iGPU+RPC setups)+ if (gpus.empty()) {model->devices.insert(model->devices.end(), igpus.begin(), igpus.end());}}