GitLab

This is faster since we only need to do atomic adds on dq, instead of atomic
adds on both dk and dv.

Previously we were using block_size=256.

They don't have to have the same block size, number of threads, etc.

as title.

Theoretically this might have lower numerical error since the scaling is in
fp32 instead of fp16 (not sure, I haven't thought too carefully about it).
However, in practice, the numerical errors seem about the same.

This speeds up the fwd by 1.5x.