BendtorchGpu.lf_b3_f: def of bendtorch-gpu@1.3.0.0
Import: import bendtorch-gpu@1.3.0.0/main.bend as BendtorchGpu
Lines 1123-1126 of bendtorch-gpu@1.3.0.0/main.bend: https://jend.leeeet.dev/read.txt?path=bendtorch-gpu@1.3.0.0/main.bend&start_line=1123&end_line=1126

import Base
import bend-ml-tensor-gpu@0.1.5.0/main.bend as TG

# x1 = q, x2 = k, x3 = dO, x4 = G; P read from the first output (unchanged), dQ, dK and dV (over V) written
def lf_b3_f(+t: U32, +l: U32, +c: EAC, x1: Array<F32>, x2: Array<F32>, x3: Array<F32>, x4: Array<F32>, o: TG.O4) -> TG.O4:
  match o:
    case TG.O4{p, dq, dk, v}: b3_o(b3_loop_f(TG.share(t, eac_n(c), l), t, l, c, S8{x1, x2, x3, x4, p, dq, dk, v}))

Uses (10):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Array
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=U32
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-gpu@0.1.5.1/main.bend&name=O4
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-gpu@0.1.5.1/main.bend&name=share
  https://jend.leeeet.dev/definition.txt?path=bendtorch-gpu@1.3.0.0/main.bend&name=EAC
  https://jend.leeeet.dev/definition.txt?path=bendtorch-gpu@1.3.0.0/main.bend&name=S8
  https://jend.leeeet.dev/definition.txt?path=bendtorch-gpu@1.3.0.0/main.bend&name=b3_loop_f
  https://jend.leeeet.dev/definition.txt?path=bendtorch-gpu@1.3.0.0/main.bend&name=b3_o
  https://jend.leeeet.dev/definition.txt?path=bendtorch-gpu@1.3.0.0/main.bend&name=eac_n