init at most one vulkan device, submodule update

fixes issues w/ multiple of the same gpu

gpt4all-backend/llama.cpp-mainline

@@ -1 +1 @@
-Subproject commit 2f7732b667b5c7786da0fa59fd612cc87b04b325
+Subproject commit e5ab32aab84c9252e865114483dbd7505e5caabb

gpt4all-chat/chatllm.cpp

@@ -279,8 +279,10 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
                         m_llModelInfo.model->initializeGPUDevice(devices.front());
                     } else {
                         for (LLModel::GPUDevice &d : availableDevices) {
-                            if (QString::fromStdString(d.name) == requestedDevice)
+                            if (QString::fromStdString(d.name) == requestedDevice) {
                                 m_llModelInfo.model->initializeGPUDevice(d);
+                                break;
+                            }
                         }
                     }
                 }