diff --git a/vllm/model_executor/models/deepseek_v2.py b/vllm/model_executor/models/deepseek_v2.py index 2c6b075ae7..144ff3971a 100644 --- a/vllm/model_executor/models/deepseek_v2.py +++ b/vllm/model_executor/models/deepseek_v2.py @@ -1470,6 +1470,9 @@ class DeepseekV2Model(nn.Module): [self.hidden_size, self.hidden_size], dim=-1 ) + if self.end_layer in self.aux_hidden_state_layers: + aux_hidden_states.append(hidden_states + residual) + hidden_states, _ = self.norm(hidden_states, residual) if len(aux_hidden_states) > 0: return hidden_states, aux_hidden_states