apache-tvm-ffi!=0.1.8,!=0.1.8.post0,<0.2,>=0.1.6
click
cuda-tile
einops
ninja
numpy
nvidia-cudnn-frontend>=1.13.0
nvidia-cutlass-dsl>=4.4.2
nvidia-ml-py
packaging>=24.2
requests
tabulate
torch
tqdm

[cu12]
nvidia-cutlass-dsl>=4.4.2

[cu13]
nvidia-cutlass-dsl[cu13]>=4.4.2
