CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)

Browse Source 
* ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type

ggml-backend : add device id to device props

llama : only use iGPU devices if there are no GPU devices

llama : do not use multiple devices from different backends with the same device id
This commit is contained in:
Diego Devesa
2025-09-11 13:47:38 -07:00
committed by GitHub
parent 0e6ff0046f
commit 360d6533db
7 changed files with 81 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tools/llama-bench/llama-bench.cpp
View File

@@ -128,7 +128,7 @@ static std::string get_gpu_info() {
for (size_t i = 0; i < ggml_backend_dev_count(); i++) {
auto * dev = ggml_backend_dev_get(i);
auto dev_type = ggml_backend_dev_type(dev);
if (dev_type == GGML_BACKEND_DEVICE_TYPE_GPU) {
if (dev_type == GGML_BACKEND_DEVICE_TYPE_GPU || dev_type == GGML_BACKEND_DEVICE_TYPE_IGPU) {
gpu_list.push_back(ggml_backend_dev_description(dev));
}
}
@@ -945,6 +945,7 @@ struct cmd_params_instance {
exit(1);
}
}
// FIXME: use llama.cpp device selection logic
// 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);
@@ -957,6 +958,10 @@ struct cmd_params_instance {
case GGML_BACKEND_DEVICE_TYPE_GPU:
devices.push_back(dev);
break;
case GGML_BACKEND_DEVICE_TYPE_IGPU:
// iGPUs are not used when there are RPC servers
break;
}
}
devices.push_back(nullptr);