law attn_par_fwd_full

bendtorch@1.3.0.0 · LAWS.bend:201

import Base
import bendtorch@1.3.0.0/main.bend as T

201# LAW (attn_par_fwd_full): the same tree law for FullAttention's forward leaf: fpar_full at any depth gives exactly
202# what fleaf_full gives running the sequences one after another, so a full-attention forward does not depend on the
203# depth or the thread count either.
204law attn_par_fwd_full:
205  for d: Nat
206  for gs: T.Halves<T.FS>
207  for +n: Nat
208  for +h: Nat
209  for +dm: T.Dm
210  {T.fpar_full(d, gs, n, h, dm) == T.fleaf_full(T.hcat(T.FS, gs), h, dm, Nil{}) : List<&1, Array<F32>>}