V100 machine

[mingzhang1998]

Hi Steven, Do you know when will the algorithm be ready for V100 machine. We only have V100 machine and the inference process returns error like that Thanks for this work btw.

[Steven-SWZhang]

Hi, thanks for your interest in our work. You can refer to this link for now to address your concerns. I haven't done a thorough validation yet, but based on our experience, the differences should be very minimal.

[MingkunLei]

@mingzhang1998 bro, have you solve this problem. i tried to change the code to 'model = model.half().to(gpu)'; but it did not work.

[mingzhang1998]

@mingzhang1998 bro, have you solve this problem. i tried to change the code to 'model = model.half().to(gpu)'; but it did not work.

Sry man. I failed to solve it. I tried several machines even including an A100 (40G), but they all give me the same error.

[MingkunLei]

@mingzhang1998 Have you tried to reisntall all the dependencies, especially the pytorch? If you solve the problem in the future, hope to send the method, thanks!

[MingkunLei]

@mingzhang1998 hey bro, I tried to upgrade my xformers to 0.0.16 then it works. Maybe you could try it.