Skip to content

llama-bench : use local GPUs along with RPC servers #14917

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 28, 2025
Merged

llama-bench : use local GPUs along with RPC servers #14917

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions tools/llama-bench/llama-bench.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -950,6 +950,7 @@ struct cmd_params_instance {
}
static std::vector<ggml_backend_dev_t> devices;
devices.clear();
// RPC devices should always come first for performance reasons
for (const std::string & server : rpc_servers) {
ggml_backend_dev_t dev = ggml_backend_rpc_add_device_fn(server.c_str());
if (dev) {
Expand All @@ -959,6 +960,20 @@ struct cmd_params_instance {
exit(1);
}
}
// add local GPU devices if any
for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
ggml_backend_dev_t dev = ggml_backend_dev_get(i);
switch (ggml_backend_dev_type(dev)) {
case GGML_BACKEND_DEVICE_TYPE_CPU:
case GGML_BACKEND_DEVICE_TYPE_ACCEL:
// skip CPU backends since they are handled separately
break;

case GGML_BACKEND_DEVICE_TYPE_GPU:
devices.push_back(dev);
break;
}
}
devices.push_back(nullptr);
mparams.devices = devices.data();
}
Expand Down
Loading