mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-04-17 12:06:10 +00:00
arg : list RPC devices first when using --list-devices (#11655)
List devices in the same order as they appear when evaluating the model and splitting tensors across devices, i.e. RPC devices come first in the list. ref #11435
This commit is contained in:
parent
db288b60cb
commit
1bef571f6a
@ -1465,15 +1465,28 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
{"--list-devices"},
|
||||
"print list of available devices and exit",
|
||||
[](common_params &) {
|
||||
printf("Available devices:\n");
|
||||
std::vector<ggml_backend_dev_t> rpc_devices;
|
||||
std::vector<ggml_backend_dev_t> all_devices;
|
||||
for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
|
||||
auto * dev = ggml_backend_dev_get(i);
|
||||
if (ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_GPU) {
|
||||
size_t free, total;
|
||||
ggml_backend_dev_memory(dev, &free, &total);
|
||||
printf(" %s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), total / 1024 / 1024, free / 1024 / 1024);
|
||||
ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(dev);
|
||||
if (ggml_backend_reg_name(reg) == std::string("RPC")) {
|
||||
rpc_devices.push_back(dev);
|
||||
} else {
|
||||
all_devices.push_back(dev);
|
||||
}
|
||||
}
|
||||
}
|
||||
// insert RPC devices in front
|
||||
all_devices.insert(all_devices.begin(), rpc_devices.begin(), rpc_devices.end());
|
||||
printf("Available devices:\n");
|
||||
for (size_t i = 0; i < all_devices.size(); ++i) {
|
||||
auto * dev = all_devices[i];
|
||||
size_t free, total;
|
||||
ggml_backend_dev_memory(dev, &free, &total);
|
||||
printf(" %s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev), total / 1024 / 1024, free / 1024 / 1024);
|
||||
}
|
||||
exit(0);
|
||||
}
|
||||
));
|
||||
|
Loading…
x
Reference in New Issue
Block a user