biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)

Browse Source 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-11-05 12:51:16 +08:00
committed by GitHub
parent 878fd5a16f
commit 428bc7bf1c
19 changed files with 107 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/api_server.py
View File

@@ -220,14 +220,8 @@ async def build_async_engine_client_from_engine_args(
# Create the EngineConfig (determines if we can use V1).
vllm_config = engine_args.create_engine_config(usage_context=usage_context)
# V1 AsyncLLM.
assert envs.VLLM_USE_V1
if disable_frontend_multiprocessing:
logger.warning(
"V1 is enabled, but got --disable-frontend-multiprocessing. "
"To disable frontend multiprocessing, set VLLM_USE_V1=0."
)
logger.warning("V1 is enabled, but got --disable-frontend-multiprocessing.")
from vllm.v1.engine.async_llm import AsyncLLM