diff --git a/deepspeed/runtime/engine.py b/deepspeed/runtime/engine.py index 93af1dda458b..d24e99af488e 100755 --- a/deepspeed/runtime/engine.py +++ b/deepspeed/runtime/engine.py @@ -2045,7 +2045,7 @@ def get_layer_state_dict(module, prefix=""): # gather one layer at a time to be memory-efficient with deepspeed.zero.GatheredParameters(list( module.parameters(recurse=False)), - modifier_rank=0): + modifier_rank=None): if torch.distributed.get_rank() == 0: for name, param in module.named_parameters(recurse=False): if param is None: