LANSHANGH

Results 2 comments of LANSHANGH

The cmake command I use is the Initial build steps in quickstart.md. `$ export CUDACXX=${CUDA_INSTALL_PATH}/bin/nvcc $ mkdir build && cd build $ cmake .. -DCUTLASS_NVCC_ARCHS=75 # compiles for NVIDIA Hopper...

What I'm trying to say is that make_tensor creates a tensor of the same shape, sometimes it works, sometimes it doesn't, and here I'm using make_tensor inside a CUDA kernel...