From 58ad3c3ad209a03a67da95d4a12d5ba7fa2ea3cd Mon Sep 17 00:00:00 2001
From: Behnam M <58621210+ibehnam@users.noreply.github.com>
Date: Wed, 10 Jan 2024 00:20:33 -0500
Subject: [PATCH] starting http server before initializing the model

---
 examples/server/server.cpp | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index d310ffc3d..29c571cd8 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -2798,7 +2798,9 @@ int main(int argc, char **argv)
                                 {"total_threads", std::thread::hardware_concurrency()},
                                 {"system_info", llama_print_system_info()},
                             });
-    
+
+    httplib::Server svr;
+
     ServerState server_state = LOADING_MODEL;
     // load the model
     if (!llama.load_model(params))
@@ -2810,7 +2812,6 @@ int main(int argc, char **argv)
     llama.initialize();
     server_state = READY;
 
-    httplib::Server svr;
 
     // Middleware for API key validation
     auto validate_api_key = [&sparams](const httplib::Request &req, httplib::Response &res) -> bool {