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 13, 22:00 UTC
[Bugfix] Python 3.10 compatibility for `Self` (#27918)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Nov 1, 2025 at 23:28 UTC
99d69af9ece094acb94901439925f8468b32326a
1 file changed
+2
-1
vllm/config/structured_outputs.py
+2
-1
@@ -2,10 +2,11 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
4
import hashlib
5
-from typing import Any, Literal, Self
5
+from typing import Any, Literal
6
7
from pydantic import model_validator
8
from pydantic.dataclasses import dataclass
9
+from typing_extensions import Self
10
11
from vllm.config.utils import config
12