diff --git a/vllm/entrypoints/cli/serve.py b/vllm/entrypoints/cli/serve.py index 8dfa19e16..c12cc7ff2 100644 --- a/vllm/entrypoints/cli/serve.py +++ b/vllm/entrypoints/cli/serve.py @@ -108,6 +108,7 @@ class ServeSubcommand(CLISubcommand): run_multi_api_server(args) else: # Single API server (this process). + args.api_server_count = None uvloop.run(run_server(args)) def validate(self, args: argparse.Namespace) -> None: