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 12, 02:15 UTC
[CI] Fix re import error (#29973)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Dec 3, 2025 at 15:16 UTC
ac1886588fd8799ff874b860b6c266a84d5a2b2b
3 files changed
+5
-4
.buildkite/scripts/generate-nightly-index.py
+2
-1
@@ -7,13 +7,14 @@
7
8
import argparse
9
import json
10
-import re
10
import sys
11
from dataclasses import asdict, dataclass
12
from pathlib import Path
13
from typing import Any
14
from urllib.parse import quote
15
16
+import regex as re
17
+
18
if not sys.version_info >= (3, 12):
19
raise RuntimeError("This script requires Python 3.12 or higher.")
20
vllm/entrypoints/serve/instrumentator/metrics.py
+1
-2
@@ -2,9 +2,8 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
4
5
-import re
6
-
5
import prometheus_client
6
+import regex as re
7
from fastapi import FastAPI, Response
8
from prometheus_client import make_asgi_app
9
from prometheus_fastapi_instrumentator import Instrumentator
vllm/tokenizers/deepseek_v32_encoding.py
+2
-1
@@ -5,9 +5,10 @@
5
# copy from https://huggingface.co/deepseek-ai/DeepSeek-V3.2/blob/main/encoding/encoding_dsv32.py
6
import copy
7
import json
8
-import re
8
from typing import Any
9
10
+import regex as re
11
+
12
# flake8: noqa: E501
13
TOOLS_SYSTEM_TEMPLATE = """## Tools
14
You have access to a set of tools you can use to answer the user's question.