[Frontend] Pass API server count to each process (#23717)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-09-20 01:15:19 +08:00
committed by GitHub
parent 7ac67ea525
commit 6c117cff7d
12 changed files with 221 additions and 51 deletions

View File

@@ -1,8 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
import dataclasses
import json
import logging
import os
@@ -327,12 +325,7 @@ def main():
if args.command == "serialize":
eng_args_dict = {f.name: getattr(args, f.name) for f in
dataclasses.fields(EngineArgs)}
engine_args = EngineArgs.from_cli_args(
argparse.Namespace(**eng_args_dict)
)
engine_args = EngineArgs.from_cli_args(args)
input_dir = tensorizer_dir.rstrip('/')
suffix = args.suffix if args.suffix else uuid.uuid4().hex