[Bugfix] Load reasoning parser plugins before headless engine config (#53124)

Signed-off-by: alexliluz <49665315+alexliluz@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
ALEX LILUZ
2026-09-15 18:31:25 +08:00
committed by GitHub
co-authored by Jiangyun Zhu
parent 24bfbd5d4d
commit 5be911ee87
2 changed files with 46 additions and 0 deletions
+4
View File
@@ -18,6 +18,7 @@ from vllm.entrypoints.launchers.cli_args import (
from vllm.entrypoints.launchers.dp_supervisor import run_dp_supervisor
from vllm.entrypoints.serve.utils.api_utils import VLLM_SUBCMD_PARSER_EPILOG
from vllm.logger import init_logger
from vllm.reasoning import ReasoningParserManager
from vllm.usage.usage_lib import UsageContext
from vllm.utils.argparse_utils import FlexibleArgumentParser
from vllm.utils.network_utils import get_tcp_uri
@@ -179,6 +180,9 @@ def run_headless(args: argparse.Namespace):
if args.api_server_count > 1:
raise ValueError("api_server_count can't be set in headless mode")
if args.reasoning_parser_plugin and len(args.reasoning_parser_plugin) > 3:
ReasoningParserManager.import_reasoning_parser(args.reasoning_parser_plugin)
# Create the EngineConfig.
engine_args = vllm.AsyncEngineArgs.from_cli_args(args)
usage_context = UsageContext.OPENAI_API_SERVER