diff --git a/vllm/model_executor/models/qwen2.py b/vllm/model_executor/models/qwen2.py index 36d9e26f9b17f..48275eb0eab1a 100644 --- a/vllm/model_executor/models/qwen2.py +++ b/vllm/model_executor/models/qwen2.py @@ -508,13 +508,11 @@ def load_weights(self, weights: Iterable[Tuple[str, self, skip_prefixes=(["lm_head."] if self.config.tie_word_embeddings else None), - ) - - load_out = loader.load_weights(weights) + ) + loader_out = loader.load_weights(weights) if current_platform.is_hpu(): torch.hpu.synchronize() - - return load_out + return loader_out class Qwen2EmbeddingModel(nn.Module, SupportsLoRA, SupportsPP):