diff --git a/fastchat/serve/vllm_worker.py b/fastchat/serve/vllm_worker.py
index b1dc54f3d..50b028afb 100644
--- a/fastchat/serve/vllm_worker.py
+++ b/fastchat/serve/vllm_worker.py
@@ -192,6 +192,7 @@ async def api_model_details(request: Request):
         "--controller-address", type=str, default="http://localhost:21001"
     )
     parser.add_argument("--model-path", type=str, default="lmsys/vicuna-7b-v1.3")
+    parser.add_argument("--quantization", type=str)
     parser.add_argument(
         "--model-names",
         type=lambda s: s.split(","),