That information on 0.5.1 would be more than welcome... Meanwhile jumping between CPU and pytorch....

I tried to have a look at the thread you link but it seems link is dead. I think you are probably right. Somehow, I suspect that somewhere in the code there is an exchange of information between CPU and GPU and if we fail to "force" it on the GPU it get somehow lost on the way... Sorry that my solution can't help you more. Hope you find a way out.