law attn_par_bwd
import bendtorch@1.3.0.0/LAWS.bend as LAWSimport Base
import bendtorch@1.3.0.0/main.bend as T
212# LAW (attn_par_bwd): the same for the backward pass: T.bpar's tree gives each sequence's dQ, dK and dV exactly as
213# T.bleaf, one sequence after another.
214law attn_par_bwd:
215 for d: Nat
216 for gs: T.Halves<T.BG>
217 for +n: Nat
218 for +kv: Nat
219 for +dm: T.Dm
220 {T.bpar(d, gs, n, kv, dm) == T.bleaf(T.hcat(T.BG, gs), kv, dm, Nil{}) : List<&1, T.DB>}
Uses (11)
Used by (0)
No other definition uses this definition.