From 213cc5c34082490f7aa88d27aa24d5eae2a39ab9 Mon Sep 17 00:00:00 2001
From: Andrei Betlen <abetlen@gmail.com>
Date: Tue, 11 Apr 2023 11:54:31 -0400
Subject: [PATCH] Remove async from function signature to avoid blocking the
 server

---
 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 44ee1f0..80cbe01 100644
--- a/llama_cpp/server/__main__.py
+++ b/llama_cpp/server/__main__.py
@@ -196,7 +196,7 @@ CreateChatCompletionResponse = create_model_from_typeddict(llama_cpp.ChatComplet
     "/v1/chat/completions",
     response_model=CreateChatCompletionResponse,
 )
-async def create_chat_completion(
+def create_chat_completion(
     request: CreateChatCompletionRequest,
 ) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:
     completion_or_chunks = llama.create_chat_completion(