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, 04:45 UTC
[Fix] import regex instead of re (#19875)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Thomas Parnell committed
Jun 20, 2025 at 13:16 UTC
7771d1de882f53863f04d609723b8c29646ee5da
1 file changed
+2
-1
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py
+2
-1
@@ -1,10 +1,11 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# ruff: noqa
3
import json
4
-import re
4
from collections.abc import Sequence
5
from typing import Any, Dict, List, Optional, Union
6
7
+import regex as re
8
+
9
from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
10
DeltaFunctionCall, DeltaMessage,
11
DeltaToolCall,