xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-12 14:35:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix io processor pooling #28273 (#28484)

Browse Source 
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
This commit is contained in:
baonudesifeizhai 2025-11-13 06:34:14 -05:00 committed by GitHub
parent 5e973209aa
commit c428e8d80b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/openai/serving_pooling.py
View File

@ -4,7 +4,7 @@
import asyncio import asyncio
import json import json
import time import time
from collections.abc import AsyncGenerator from collections.abc import AsyncGenerator, Sequence
from typing import Final, cast from typing import Final, cast
import jinja2 import jinja2
@ -122,6 +122,10 @@ class OpenAIServingPooling(OpenAIServing):
engine_prompts = await self.io_processor.pre_process_async( engine_prompts = await self.io_processor.pre_process_async(
prompt=validated_prompt, request_id=request_id prompt=validated_prompt, request_id=request_id
) )
if not isinstance(engine_prompts, Sequence) or isinstance(
engine_prompts, (str, bytes, bytearray)
):
engine_prompts = [engine_prompts]
elif isinstance(request, PoolingChatRequest): elif isinstance(request, PoolingChatRequest):
error_check_ret = self._validate_chat_template( error_check_ret = self._validate_chat_template(