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
[Refactor] Remove unused library (#20099)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Jun 26, 2025 at 05:16 UTC
d188913d99bbdfc699bc4f7c2c23187f3745f94b
1 file changed
-1
vllm/_custom_ops.py
-1
@@ -5,7 +5,6 @@ import contextlib
5
from typing import TYPE_CHECKING, Optional, Union
6
7
import torch
8
-import torch.library
8
9
import vllm.envs as envs
10
from vllm.logger import init_logger