Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions colossalai/shardformer/policies/deepseek.py
Original file line number Diff line number Diff line change
Expand Up @@ -332,6 +332,7 @@ def get_held_layers(self) -> List[Module]:
assert stage_manager.num_model_chunks is not None
layers_per_stage = stage_manager.distribute_layers(len(module.layers))
stage_indices = stage_manager.get_stage_index(layers_per_stage)
stage_manager.stage_indices = stage_indices
if stage_manager.is_first_stage(ignore_chunk=True):
held_layers.append(module.embed_tokens)
for start_idx, end_idx in stage_indices:
Expand Down