feat: set n_threads=2

main.py

@@ -2,10 +2,9 @@ from llama_cpp.server.app import create_app, Settings
 from fastapi.responses import HTMLResponse
 import os
 
-print("os.cpu_count()", os.cpu_count())
 app = create_app(
     Settings(
-        n_threads=os.cpu_count(),
+        n_threads=2, # set to number of cpu cores
         model="model/ggmlv3-model.bin",
         embedding=False
     )