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

[Bugfix] Fix SHM cache initialization (#26427)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-10-09 17:48:04 +08:00
committed by GitHub
parent dc7976dd9f
commit 4bdf7ac593
30 changed files with 357 additions and 417 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/entrypoints/openai/serving_tokenization.py
View File

@@ -6,7 +6,6 @@ from typing import Any, Final, Optional, Union
import jinja2
from fastapi import Request
from vllm.config import ModelConfig
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
from vllm.entrypoints.logger import RequestLogger
@@ -32,7 +31,6 @@ class OpenAIServingTokenization(OpenAIServing):
def __init__(
self,
engine_client: EngineClient,
model_config: ModelConfig,
models: OpenAIServingModels,
*,
request_logger: Optional[RequestLogger],
@@ -43,7 +41,6 @@ class OpenAIServingTokenization(OpenAIServing):
) -> None:
super().__init__(
engine_client=engine_client,
model_config=model_config,
models=models,
request_logger=request_logger,
log_error_stack=log_error_stack,