Commit f477f795c for llama.cpp

commit f477f795cb071baf5b8af6488378366a72034ac4
Author: Georgi Gerganov <ggerganov@gmail.com>
Date:   Sun Nov 8 02:29:52 2026 +0200

    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)

diff --git a/tools/server/server-models.cpp b/tools/server/server-models.cpp
index 38fb76950..fa0f09e71 100644
--- a/tools/server/server-models.cpp
+++ b/tools/server/server-models.cpp
@@ -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()) {