diff --git a/python/sglang/srt/models/deepseek_v2.py b/python/sglang/srt/models/deepseek_v2.py index 26c5e617a..2cd64d532 100644 --- a/python/sglang/srt/models/deepseek_v2.py +++ b/python/sglang/srt/models/deepseek_v2.py @@ -1628,7 +1628,7 @@ class DeepseekV2ForCausalLM(nn.Module): f"mlp.experts." f"{self.config.n_routed_experts + num_repeat}" f".{suffix}", - weights_dict[shared_expert_weight_name].clone(), + weights_dict[shared_expert_weight_name], ) ) names_to_remove += [shared_expert_weight_name]