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 11, 18:45 UTC
[Misc] Fix safetensors import for safe_open (#30300)
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Yongtao Huang committed
Dec 9, 2025 at 14:50 UTC
e4605d225e020154bc98efd15a05e11b83eaefb7
1 file changed
+1
-1
vllm/lora/lora_model.py
+1
-1
@@ -3,7 +3,7 @@
3
4
import os
5
6
-import safetensors.torch
6
+import safetensors
7
import torch
8
9
from vllm.logger import init_logger