Update main.py

main.py

@@ -50,7 +50,7 @@ logger.info("Finished loading models!")
 # Initialize FastAPI app
 app = FastAPI()
 
-MAX_QUEUE_SIZE = 10  # Set a reasonable limit based on your system capacity
+MAX_QUEUE_SIZE = 20  # Set a reasonable limit based on your system capacity
 request_queue = asyncio.Queue(maxsize=MAX_QUEUE_SIZE)
 
 # Define response model