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 8, 19:00 UTC
Fix `main` pre-commit (#33975)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Feb 6, 2026 at 08:08 UTC
6d8d34be6dcaff0f5aa6de245adffc2bac5b2d3e
1 file changed
+1
-1
vllm/model_executor/models/voyage.py
+1
-1
@@ -2,10 +2,10 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
from __future__ import annotations
4
5
-import re
5
from collections import defaultdict
6
from collections.abc import Iterable
7
8
+import regex as re
9
import torch
10
import torch.nn as nn
11