[V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612)

Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
Flora Feng
2026-03-20 11:31:43 +08:00
committed by GitHub
parent 8fbe3f303f
commit 9040151fe1
10 changed files with 8 additions and 73 deletions
-9
View File
@@ -181,7 +181,6 @@ async def run_vllm_async(
n: int,
engine_args: AsyncEngineArgs,
do_profile: bool,
disable_frontend_multiprocessing: bool = False,
disable_detokenize: bool = False,
) -> float:
from vllm import SamplingParams
@@ -191,7 +190,6 @@ async def run_vllm_async(
async with build_async_engine_client_from_engine_args(
engine_args,
disable_frontend_multiprocessing=disable_frontend_multiprocessing,
) as llm:
model_config = llm.model_config
assert all(
@@ -757,12 +755,6 @@ def add_cli_args(parser: argparse.ArgumentParser):
default=False,
help="Use vLLM async engine rather than LLM class.",
)
parser.add_argument(
"--disable-frontend-multiprocessing",
action="store_true",
default=False,
help="Disable decoupled async engine frontend.",
)
parser.add_argument(
"--disable-detokenize",
action="store_true",
@@ -880,7 +872,6 @@ def main(args: argparse.Namespace):
requests,
args.n,
AsyncEngineArgs.from_cli_args(args),
disable_frontend_multiprocessing=args.disable_frontend_multiprocessing,
disable_detokenize=args.disable_detokenize,
do_profile=args.profile,
)