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, 03:30 UTC
[Misc] remove unused import (#20517)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jul 6, 2025 at 10:17 UTC
8d763cb891245278fba3c458c2e7d05380b559f6
1 file changed
+1
-1
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py
+1
-1
@@ -3,7 +3,7 @@
3
# ruff: noqa
4
import json
5
from collections.abc import Sequence
6
-from typing import Any, Dict, List, Optional, Union
6
+from typing import Any, Optional, Union
7
8
import regex as re
9