Karn Tiwari
Karn Tiwari
Yeah, I am using your codebase for one of my projects and the deadline is next month. Was testing some architectures and needed layer norm for that so would be...
@mdchuc, do you have any idea why, in code, they are flipping the out_b across the dim=-1? Shouldn't it be dim = 1?
Hi @zzzendurance , It should be 1 right? As I do think in out_b it should be out_b.flip([1]) instead of -1. As we need to flip the tokens not the...
> > Hi @zzzendurance , It should be 1 right? As I do think in out_b it should be out_b.flip([1]) instead of -1. As we need to flip the tokens...
I had Triton 2.0.0 and then installed 2.3.1 and it worked.