Update inference_test.py

inference_test.py

@@ -160,7 +160,7 @@ async def chat(msg: llm_model.Message, request: Request):
         traceback.print_exc()
         return JSONResponse(content={"error": str(e)}, status_code=500)
 
-threading.Thread(target=llm_model.setup_model, kwargs={"service_config": s_config}, daemon=True).start()
+threading.Thread(target=llm_model.setup_model, kwargs={"app_config": s_config}, daemon=True).start()
 threading.Thread(target=lambda: uvicorn.run(app, host="0.0.0.0", port=7860), daemon=True).start()
 while True:
     time.sleep(60)