diff --git a/python/sglang/srt/model_loader/weight_utils.py b/python/sglang/srt/model_loader/weight_utils.py index b71f9ff3d..2f21d55c0 100644 --- a/python/sglang/srt/model_loader/weight_utils.py +++ b/python/sglang/srt/model_loader/weight_utils.py @@ -457,7 +457,6 @@ def pt_weights_iterator( state = torch.load(bin_file, map_location="cpu", weights_only=True) yield from state.items() del state - torch.cuda.empty_cache() def get_gguf_extra_tensor_names(