liangyx

> I actually worked on that. The precomputing part is that part implemented in CPP. They converted it using CMAKE and SWIG, so I was not able to utilize them...

I think it is the problem of the data itself, delete the piece of data that reported the error in json, and it works fine. ---Original--- From: ***@***.***> Date: Thu,...

Thank you for your reply. But my cuda version is 10.1 torch version is 1.12. Can I solve this problem without upgrading?

I mean if I want to install torch-sparse 0.6.16, I need the following dependency ring: torch1.13->cuda11.6. However, my cuda only works with version 10.2 due to some utility restrictions, so...

I tried to upgrade torch-sparse 0.6.16, however, I got a new error when running the previous code, is there any solution? RuntimeError (note: full exception trace is shown but execution...

torch_sparse.__version__ return '0.6.16+pt113cu116'

Hi, do you have any idea about this problem? thanks for help

[matmul.txt](https://github.com/rusty1s/pytorch_sparse/files/10979109/matmul.txt)

Yes, running the above code will report the following error. AttributeError: 'Tensor' object has no attribute 'to_torch_coo_tensor' However, my torch has been upgraded to 1.13.1. use torch.__version__ return: '1.13.1+cu116'

Running the above code is successful :(