server : downgrade per-request proxy logs to trace (#31859)

Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)
This commit is contained in:
Georgi Gerganov authored and GitHub committed 2026-11-08 01:29:52 +01:00
1 parent 76a67730ff
commit f477f795cb
1 file changed
+2 -2
+2 -2
View File
@@ -1702,7 +1702,7 @@ server_http_res_ptr server_models::proxy_request(const server_http_req & req, co
// sleep after req_count++, so the model counts as busy while we wait here
std::this_thread::sleep_for(std::chrono::seconds(2));
}
SRV_INF("proxying request to model %s on port %d\n", name.c_str(), meta->port);
SRV_TRC("proxying request to model %s on port %d\n", name.c_str(), meta->port);
std::string proxy_path = req.path;
if (!req.query_string.empty()) {
proxy_path += '?' + req.query_string;
@@ -1757,7 +1757,7 @@ void server_models::proxy_ws(const server_http_req & req, server_http_context::w
mapping[name].meta.last_used = ggml_time_ms();
mapping[name].req_count++;
}
SRV_INF("proxying websocket to model %s on port %d\n", name.c_str(), meta->port);
SRV_TRC("proxying websocket to model %s on port %d\n", name.c_str(), meta->port);
std::string url = std::string("ws://") + CHILD_ADDR + ":" + std::to_string(meta->port) + req.path;
if (!req.query_string.empty()) {