# clone the repository
git clone https://github.com/hpcaitech/ColossalAI.git
cd ColossalAI

# download the cub library
wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
unzip 1.8.0.zip
cp -r cub-1.8.0/cub/ colossalai/kernel/cuda_native/csrc/kernels/include/

# install
BUILD_EXT=1 pip install .