API server support ipv4 / ipv6 dualstack (#1288)

Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

examples/gradio_webserver.py

@@ -39,7 +39,7 @@ def build_demo():
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("--host", type=str, default="localhost")
+    parser.add_argument("--host", type=str, default=None)
     parser.add_argument("--port", type=int, default=8001)
     parser.add_argument("--model-url",
                         type=str,

vllm/entrypoints/api_server.py

@@ -65,7 +65,7 @@ async def generate(request: Request) -> Response:
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("--host", type=str, default="localhost")
+    parser.add_argument("--host", type=str, default=None)
     parser.add_argument("--port", type=int, default=8000)
     parser = AsyncEngineArgs.add_cli_args(parser)
     args = parser.parse_args()

vllm/entrypoints/openai/api_server.py

@@ -567,10 +567,7 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="vLLM OpenAI-Compatible RESTful API server.")
-    parser.add_argument("--host",
-                        type=str,
-                        default="localhost",
-                        help="host name")
+    parser.add_argument("--host", type=str, default=None, help="host name")
     parser.add_argument("--port", type=int, default=8000, help="port number")
     parser.add_argument("--allow-credentials",
                         action="store_true",