AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

When device is Auto (the default) then we will only consider discrete GPU's otherwise fallback to CPU.

Browse Source
This commit is contained in:
Adam Treat 2023-09-13 11:59:36 -04:00
parent 8f99dca70f
commit 891ddafc33
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-chat/chatllm.cpp
View File

@ -275,7 +275,7 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
if (requestedDevice != "CPU") {
const size_t requiredMemory = m_llModelInfo.model->requiredMem(filePath.toStdString());
std::vector<LLModel::GPUDevice> availableDevices = m_llModelInfo.model->availableGPUDevices(requiredMemory);
if (!availableDevices.empty() && requestedDevice == "Auto") {
if (!availableDevices.empty() && requestedDevice == "Auto" && devices.front().type == 2 /*a discrete gpu*/) {
m_llModelInfo.model->initializeGPUDevice(devices.front());
} else {
for (LLModel::GPUDevice &d : availableDevices) {