diff --git a/vllm/model_executor/layers/layernorm.py b/vllm/model_executor/layers/layernorm.py index cb3cee2bad5a..1d752730cbf8 100644 --- a/vllm/model_executor/layers/layernorm.py +++ b/vllm/model_executor/layers/layernorm.py @@ -49,6 +49,8 @@ def forward( residual: Optional[torch.Tensor] = None, ) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]: if residual is not None: + if isinstance(x, tuple): + x = x[0] ops.fused_add_rms_norm( x, residual,