From da539cc2ee8ce0af2c5519c84b836ad1c9a64a9a Mon Sep 17 00:00:00 2001
From: Andrei Betlen <abetlen@gmail.com>
Date: Thu, 6 Apr 2023 21:22:19 -0400
Subject: [PATCH] Safer calculation of default n_threads

---
 llama_cpp/server/__main__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llama_cpp/server/__main__.py b/llama_cpp/server/__main__.py
index c3168b4..d19c45a 100644
--- a/llama_cpp/server/__main__.py
+++ b/llama_cpp/server/__main__.py
@@ -28,7 +28,7 @@ class Settings(BaseSettings):
     model: str
     n_ctx: int = 2048
     n_batch: int = 8
-    n_threads: int = int(os.cpu_count() / 2) or 1
+    n_threads: int = ((os.cpu_count() or 2) // 2) or 1
     f16_kv: bool = True
     use_mlock: bool = False     # This causes a silent failure on platforms that don't support mlock (e.g. Windows) took forever to figure out...
     embedding: bool = True