flashinfer.cake_mhc_nondet_train.cake_mhc_nondet_train_finish

flashinfer.cake_mhc_nondet_train.cake_mhc_nondet_train_finish(X: Tensor, B: Tensor, handle) → Tensor

Autograd-enabled forward_finish: Y from X, the branch output B and the prepare handle.

The arguments and output are those of cake_mhc_det_train_finish(); handle is the handle cake_mhc_nondet_train_prepare() returned (any other handle, such as a cake_mhc_det_train_prepare one, raises TypeError).

Parameters:
Returns:

BF16 Y of shape [T, 4, H].

Return type:

torch.Tensor