diff --git a/colossalai/shardformer/layer/__init__.py b/colossalai/shardformer/layer/__init__.py index 0c44e6621..c4586d18b 100644 --- a/colossalai/shardformer/layer/__init__.py +++ b/colossalai/shardformer/layer/__init__.py @@ -3,10 +3,11 @@ from .embedding import Embedding1D, VocabParallelEmbedding1D from .linear import Linear1D_Col, Linear1D_Row from .loss import cross_entropy_1d from .normalization import FusedLayerNorm, FusedRMSNorm +from .parallel_module import ParallelModule from .qkv_fused_linear import FusedLinear1D_Col, GPT2FusedLinearConv1D_Col, GPT2FusedLinearConv1D_Row __all__ = [ "Embedding1D", "VocabParallelEmbedding1D", "Linear1D_Col", "Linear1D_Row", 'GPT2FusedLinearConv1D_Col', 'GPT2FusedLinearConv1D_Row', 'DropoutForParallelInput', 'DropoutForReplicatedInput', "cross_entropy_1d", - 'FusedLayerNorm', 'FusedRMSNorm', 'FusedLinear1D_Col' + 'FusedLayerNorm', 'FusedRMSNorm', 'FusedLinear1D_Col', 'ParallelModule' ]