Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on RWKV: Reinventing RNNs for the Transformer Era. Parent comment
> the equations of the RWKV model enable computational parallelization, provided that the sequence is predetermined.
And sure, this is the core concept of self attention, no?
There are no comments on this comment yet.
> the equations of the RWKV model enable computational parallelization, provided that the sequence is predetermined.
And sure, this is the core concept of self attention, no?