diff --git a/vllm/model_executor/models/deepseek_v2.py b/vllm/model_executor/models/deepseek_v2.py index b5409c7fe1b7..72283f5df1b9 100644 --- a/vllm/model_executor/models/deepseek_v2.py +++ b/vllm/model_executor/models/deepseek_v2.py @@ -146,6 +146,7 @@ def __init__( hidden_act=config.hidden_act, quant_config=quant_config, reduce_results=False, + prefix=f"{prefix}.shared_experts", ) def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: