Skip to content
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

Jump to bottom

[LLM] Reconstruct fused transformer layers #7186

Merged
merged 5 commits into from
Oct 12, 2023
Merged

[LLM] Reconstruct fused transformer layers #7186

merged 5 commits into from
Oct 12, 2023

Conversation

RichardWooSJTU
Copy link
Contributor

PR types

Function optimization

PR changes

Others

Description

Reconstruct class FusedMultiTransformer

  • Add FusedMultiTransformerConfig
  • Add FusedMultiTransformerBase
  • Add FusedMultiTransformerWeightonly
  • Add FusedMultiTransformerPostLayernorm
  • Add FusedMultiTransformerWeightonlyPostLayernorm

@paddle-bot
Copy link

paddle-bot bot commented Oct 10, 2023

Thanks for your contribution!

@RichardWooSJTU RichardWooSJTU changed the title Reconstruct fused transformer layers [LLM] Reconstruct fused transformer layers Oct 10, 2023
@codecov
Copy link

codecov bot commented Oct 10, 2023 •
edited
Loading

Codecov Report

Merging #7186 (c3dcf12) into develop (74eb855) will decrease coverage by 0.06%.
The diff coverage is 0.00%.

@@             Coverage Diff             @@
##           develop    #7186      +/-   ##
===========================================
- Coverage    59.39%   59.33%   -0.06%     
===========================================
  Files          567      567              
  Lines        83114    83190      +76     
===========================================
  Hits         49364    49364              
- Misses       33750    33826      +76
Files Coverage Δ
...dlenlp/experimental/transformers/bloom/modeling.py 0.00% <0.00%> (ø)
...enlp/experimental/transformers/chatglm/modeling.py 0.00% <0.00%> (ø)
...addlenlp/experimental/transformers/gpt/modeling.py 0.00% <0.00%> (ø)
...addlenlp/experimental/transformers/opt/modeling.py 0.00% <0.00%> (ø)
...dlenlp/experimental/transformers/llama/modeling.py 0.00% <0.00%> (ø)
...erimental/transformers/fused_transformer_layers.py 0.00% <0.00%> (ø)

@wj-Mcat
Copy link
Contributor

wj-Mcat commented Oct 11, 2023

这个PR 导致之前的推理单测挂了：https://xly.bce.baidu.com/paddlepaddle/Paddle-NLP/newipipe/detail/9304392/job/24091206

这样看来可能会影响之前模型的精度。

@wj-Mcat
Copy link
Contributor

wj-Mcat commented Oct 11, 2023

合入 #7187 之后你这边有冲突，麻烦解决一下冲突。

wj-Mcat
wj-Mcat approved these changes Oct 12, 2023
View reviewed changes
Copy link
Contributor

@wj-Mcat wj-Mcat left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@wj-Mcat wj-Mcat merged commit 64f00f0 into PaddlePaddle:develop Oct 12, 2023
4 checks passed
@ZHUI ZHUI mentioned this pull request Jan 2, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@heavengate heavengate heavengate approved these changes

@wj-Mcat wj-Mcat wj-Mcat approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@RichardWooSJTU @wj-Mcat @heavengate