Skip to content

move fused_layers.py from PaddleNLP to Paddle #10867

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

move fused_layers.py from PaddleNLP to Paddle #10867

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
55ad83d
move fused_layers.py to Paddle
GITD245 Jul 18, 2025
d59960d
change import path
GITD245 Jul 18, 2025
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
2 changes: 1 addition & 1 deletion llm/auto_parallel/deepseek-v3/run_pretrain_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,7 +476,7 @@ def main():
if (
do_enable_linear_fused_grad_add or do_enable_mp_async_allreduce or do_enable_sp_async_reduce_scatter
) and not training_args.to_static:
from llm.utils.fused_layers import mock_layers
from paddle.incubate.nn import mock_layers

mock_layers(do_enable_linear_fused_grad_add, do_enable_mp_async_allreduce, do_enable_sp_async_reduce_scatter)

Expand Down
2 changes: 1 addition & 1 deletion llm/auto_parallel/gpt-3/run_pretrain_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -460,7 +460,7 @@ def main():
if (
do_enable_linear_fused_grad_add or do_enable_mp_async_allreduce or do_enable_sp_async_reduce_scatter
) and not training_args.to_static:
from llm.utils.fused_layers import mock_layers
from paddle.incubate.nn import mock_layers

mock_layers(do_enable_linear_fused_grad_add, do_enable_mp_async_allreduce, do_enable_sp_async_reduce_scatter)

Expand Down
6 changes: 3 additions & 3 deletions llm/auto_parallel/llama/run_pretrain_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -411,12 +411,12 @@ def init_seed(seed: int = 1234, args=None):
elif args.hybrid_parallel_topo_order == "sharding_first":
order = ["dp", "sharding", "pp", "mp", "sep"]
if args.context_parallel_degree is not None and args.context_parallel_degree > 1:
sep_degree = args.context_parallel_degree
sep_degree = args.context_parallel_degree
elif args.sep_parallel_degree is not None and args.sep_parallel_degree > 1:
sep_degree = args.sep_parallel_degree
else:
sep_degree = 1
sep_degree=args.sep_parallel_degree if args.sep_parallel_degree > 1 else args.context_parallel_degree
sep_degree = args.sep_parallel_degree if args.sep_parallel_degree > 1 else args.context_parallel_degree
topo = Topology(
dist.get_rank(),
dist.get_world_size(),
Expand Down Expand Up @@ -480,7 +480,7 @@ def main():
if (
do_enable_linear_fused_grad_add or do_enable_mp_async_allreduce or do_enable_sp_async_reduce_scatter
) and not training_args.to_static:
from llm.utils.fused_layers import mock_layers
from paddle.incubate.nn import mock_layers

mock_layers(do_enable_linear_fused_grad_add, do_enable_mp_async_allreduce, do_enable_sp_async_reduce_scatter)

Expand Down
2 changes: 1 addition & 1 deletion llm/auto_parallel/qwen/run_pretrain_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,7 +449,7 @@ def main():
if (
do_enable_linear_fused_grad_add or do_enable_mp_async_allreduce or do_enable_sp_async_reduce_scatter
) and not training_args.to_static:
from llm.utils.fused_layers import mock_layers
from paddle.incubate.nn import mock_layers

mock_layers(do_enable_linear_fused_grad_add, do_enable_mp_async_allreduce, do_enable_sp_async_reduce_scatter)

Expand Down
2 changes: 1 addition & 1 deletion llm/run_pretrain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,7 +363,7 @@ def main():
training_args.no_recompute_layers.sort()

if training_args.enable_linear_fused_grad_add:
from utils.fused_layers import mock_layers
from paddle.incubate.nn import mock_layers

mock_layers()

Expand Down
311 changes: 0 additions & 311 deletions llm/utils/fused_layers.py
View file
Open in desktop

This file was deleted.

Loading
Loading