Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-11 04:56:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix common_params_print_info

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-20 01:20:30 +02:00
parent a138f8d630
commit fc9969c725
3 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server.cpp
+4 -2
View File
@@ -132,8 +132,10 @@ int llama_server(common_params & params, int argc, char ** argv) {
const bool is_router_server = params.model.path.empty()
&& params.model.hf_repo.empty();
// skip device enumeration so the CUDA primary context stays uncreated
common_params_print_info(params, !is_router_server);
// may skip device enumeration so the CUDA primary context stays uncreated
if (!server_sleep_rst::is_boot_to_sleep()) {
common_params_print_info(params, !is_router_server);
}
if (!is_router_server) {
// validate batch size for embeddings