thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

server: (router) allow child process to report status via stdout (#18110)

Browse source 
* server: (router) allow child process to report status via stdout

* apply suggestions
This commit is contained in:
Xuan-Son Nguyen 2025-12-17 14:54:11 +01:00 • committed by GitHub
parent 8faa87db02
commit bde461de8c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 21 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tools/server/server.cpp
View file

@ -153,7 +153,6 @@ int main(int argc, char ** argv, char ** envp) {
routes.get_models = models_routes->get_router_models;
ctx_http.post("/models/load", ex_wrapper(models_routes->post_router_models_load));
ctx_http.post("/models/unload", ex_wrapper(models_routes->post_router_models_unload));
ctx_http.post("/models/status", ex_wrapper(models_routes->post_router_models_status));
}
ctx_http.get ("/health", ex_wrapper(routes.get_health)); // public endpoint (no API key check)
@ -291,7 +290,7 @@ int main(int argc, char ** argv, char ** envp) {
const char * router_port = std::getenv("LLAMA_SERVER_ROUTER_PORT");
std::thread monitor_thread;
if (router_port != nullptr) {
monitor_thread = server_models::setup_child_server(params, std::atoi(router_port), params.model_alias, shutdown_handler);
monitor_thread = server_models::setup_child_server(shutdown_handler);
}
// this call blocks the main thread until queue_tasks.terminate() is called