From c6c2855c80e6cf6ebd55602f6fe43d80aaca7fae Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sun, 27 Apr 2025 21:22:21 -0700
Subject: [PATCH] llama.cpp: Remove the timeout while loading models (closes
 #6907)

---
 modules/llama_cpp_server.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/modules/llama_cpp_server.py b/modules/llama_cpp_server.py
index 9572d5aa..4b01c228 100644
--- a/modules/llama_cpp_server.py
+++ b/modules/llama_cpp_server.py
@@ -340,9 +340,7 @@ class LlamaServer:
 
         # Wait for server to be healthy
         health_url = f"http://127.0.0.1:{self.port}/health"
-        start_time = time.time()
-        timeout = 3600 * 8  # 8 hours
-        while time.time() - start_time < timeout:
+        while True:
             # Check if process is still alive
             if self.process.poll() is not None:
                 # Process has terminated
@@ -357,8 +355,6 @@ class LlamaServer:
                 pass
 
             time.sleep(1)
-        else:
-            raise TimeoutError(f"Server health check timed out after {timeout} seconds")
 
         # Server is now healthy, get model info
         self._get_vocabulary_size()