[Frontend] Disallow passing model as both argument and option (#7347)

vllm/scripts.py

@@ -9,6 +9,7 @@ from typing import List, Optional
 from openai import OpenAI
 from openai.types.chat import ChatCompletionMessageParam
 
+from vllm.engine.arg_utils import EngineArgs
 from vllm.entrypoints.openai.api_server import run_server
 from vllm.entrypoints.openai.cli_args import make_arg_parser
 from vllm.utils import FlexibleArgumentParser
@@ -24,6 +25,12 @@ def register_signal_handlers():
 
 
 def serve(args: argparse.Namespace) -> None:
+    # The default value of `--model`
+    if args.model != EngineArgs.model:
+        raise ValueError(
+            "With `vllm serve`, you should provide the model as a "
+            "positional argument instead of via the `--model` option.")
+
     # EngineArgs expects the model name to be passed as --model.
     args.model = args.model_tag