From a21076ed3a4077e79afe0a3b422f89f9a920154d Mon Sep 17 00:00:00 2001 From: Yanyi Liu Date: Sun, 9 Mar 2025 20:13:31 +0800 Subject: [PATCH] [Misc] Ensure out-of-tree quantization method recognize by cli args (#14328) Signed-off-by: liuyanyi --- vllm/engine/arg_utils.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py index 351ac175e3e9..0d285acd15f3 100644 --- a/vllm/engine/arg_utils.py +++ b/vllm/engine/arg_utils.py @@ -1478,15 +1478,15 @@ class AsyncEngineArgs(EngineArgs): @staticmethod def add_cli_args(parser: FlexibleArgumentParser, async_args_only: bool = False) -> FlexibleArgumentParser: + # Initialize plugin to update the parser, for example, The plugin may + # adding a new kind of quantization method to --quantization argument or + # a new device to --device argument. + load_general_plugins() if not async_args_only: parser = EngineArgs.add_cli_args(parser) parser.add_argument('--disable-log-requests', action='store_true', help='Disable logging requests.') - # Initialize plugin to update the parser, for example, The plugin may - # adding a new kind of quantization method to --quantization argument or - # a new device to --device argument. - load_general_plugins() from vllm.platforms import current_platform current_platform.pre_register_and_update(parser) return parser