🐛 Bug

Type of bits in L82 should be _int.

Environment

PyTorch version: 1.8.1+cu111
Is debug build: False
CUDA used to build PyTorch: 11.1
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 10 Pro for Workstations
GCC version: Could not collect
Clang version: Could not collect
CMake version: version 3.19.1
Libc version: N/A

Python version: 3.9 (64-bit runtime)
Python platform: Windows-10-10.0.21387-SP0
Is CUDA available: True
CUDA runtime version: 11.1.105
GPU models and configuration:
GPU 0: NVIDIA Quadro P2000 with Max-Q Design
GPU 1: NVIDIA GeForce RTX 3070

Nvidia driver version: 470.14
cuDNN version: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1\bin\cudnn_ops_train64_8.dll
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] kmeans-pytorch==0.3
[pip3] numpy==1.20.3
[pip3] torch==1.8.1+cu111
[pip3] torchaudio==0.8.1
[pip3] torchvision==0.9.1+cu111
[conda] Could not collect

cc @ezyang @malfet @rgommers @xuzhao9 @gramster