A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 02:15 UTC
Removing redundant python version check (#20888)
Signed-off-by: Dannyso05 <dansong1177@gmail.com>
Daniel song committed
Jul 14, 2025 at 02:15 UTC
88fc8a97e38238dd08e2a38870a4b977e50e375f
1 file changed
-5
vllm/entrypoints/openai/serving_engine.py
-5
@@ -18,11 +18,6 @@ from pydantic import BaseModel, ConfigDict, Field
18
from starlette.datastructures import Headers
19
from typing_extensions import TypeIs
20
21
-if sys.version_info >= (3, 12):
22
- from typing import TypedDict
23
-else:
24
- from typing_extensions import TypedDict
25
-
21
if sys.version_info >= (3, 12):
22
from typing import TypedDict
23
else: