Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion megatron/core/transformer/moe/router.py
Original file line number Diff line number Diff line change
Expand Up @@ -545,7 +545,11 @@ def apply_z_loss(self, logits, padding_mask: Optional[torch.Tensor] = None):
layer_number = self.layer_number

save_to_aux_losses_tracker(
"z_loss", z_loss / moe_z_loss_coeff, layer_number, num_layers
"z_loss",
z_loss / moe_z_loss_coeff,
layer_number,
num_layers,
avg_group=self.tp_dp_cp_group,
)
return logits

Expand Down
Loading