upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

logs : reduce v2 (#25078)

Browse Source 
* server : reduce logs

* cont : common

* cont : spec

* cont : CMN_ -> COM_
This commit is contained in:
Georgi Gerganov
2026-06-28 08:52:15 +03:00
committed by GitHub
parent ebd048fc5e
commit 27c8bb4f63
12 changed files with 203 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/server/server.cpp
View File

@@ -124,7 +124,7 @@ int llama_server(int argc, char ** argv) {
}
if (params.n_parallel < 0) {
SRV_INF("%s", "n_parallel is set to auto, using n_parallel = 4 and kv_unified = true\n");
SRV_TRC("%s", "n_parallel is set to auto, using n_parallel = 4 and kv_unified = true\n");
params.n_parallel = 4;
params.kv_unified = true;
@@ -338,7 +338,7 @@ int llama_server(int argc, char ** argv) {
std::function<void()> clean_up;
if (is_router_server) {
SRV_INF("%s", "starting router server, no model will be loaded in this process\n");
SRV_INF("%s", "starting server in router mode. models will be automatically loaded on-demand\n");
clean_up = [&models_routes]() {
SRV_INF("%s: cleaning up before exit...\n", __func__);
@@ -391,9 +391,6 @@ int llama_server(int argc, char ** argv) {
});
}
// load the model
SRV_INF("%s", "loading model\n");
if (!ctx_server.load_model(params)) {
clean_up();
if (ctx_http.thread.joinable()) {
@@ -429,8 +426,9 @@ int llama_server(int argc, char ** argv) {
SetConsoleCtrlHandler(reinterpret_cast<PHANDLER_ROUTINE>(console_ctrl_handler), true);
#endif
SRV_INF("listening on %s\n", ctx_http.listening_address.c_str());
if (is_router_server) {
SRV_INF("router server is listening on %s\n", ctx_http.listening_address.c_str());
SRV_WRN("%s", "NOTE: router mode is experimental\n");
SRV_WRN("%s", " it is not recommended to use this mode in untrusted environments\n");
@@ -446,8 +444,6 @@ int llama_server(int argc, char ** argv) {
// when the HTTP server stops, clean up and exit
clean_up();
} else {
SRV_INF("server is listening on %s\n", ctx_http.listening_address.c_str());
// optionally, notify router server that this instance is ready
std::thread monitor_thread;
if (child.is_child()) {