diff --git a/deepspeed/inference/v2/model_implementations/phi3/model.py b/deepspeed/inference/v2/model_implementations/phi3/model.py index 5371a0021e5c1..2139025fbe898 100644 --- a/deepspeed/inference/v2/model_implementations/phi3/model.py +++ b/deepspeed/inference/v2/model_implementations/phi3/model.py @@ -198,7 +198,6 @@ def forward(self, wrapped_batch: RaggedBatchWrapper) -> torch.Tensor: residual = self._forward_embed(wrapped_batch) for layer_idx in range(self.num_layers): - residual, _ = self._forward_transformer_layer(layer_idx, residual, None, - wrapped_batch) + residual, _ = self._forward_transformer_layer(layer_idx, residual, None, wrapped_batch) return self._forward_unembed(residual, wrapped_batch)