Y Song
Y Song
> Thanks for contributing, can you @yiyousong add tests to your contribution? This will improve the robustness of the code > > @yzhangcs could you please give some comments? tests:...
> @yiyousong Hello, could you please explain more on what does this arg mean and what's the purpose of imposing this arg Linear attention without normalization equals to $\phi(Q)\phi(K)V$ or...
> @yiyousong Hello r u still working on this PR? I was evaluating using my own code. (only used fla.ops, not fla.layers). Based on my experience, I believe although the...
These changes are based on the code I changed to work for my model. I probably won't work on this further. Maybe after May 15th I may continue to update...