Skip to content

[AutoParallel] Add FLAGS_enable_fused_ffn_qkv_pass for llama#9182

Merged
ZHUI merged 2 commits into
PaddlePaddle:developfrom
zhangbo9674:dev/add_ffn_qkv_v2
Sep 25, 2024
Merged

[AutoParallel] Add FLAGS_enable_fused_ffn_qkv_pass for llama#9182
ZHUI merged 2 commits into
PaddlePaddle:developfrom
zhangbo9674:dev/add_ffn_qkv_v2

Conversation

@zhangbo9674
Copy link
Copy Markdown
Contributor

PR types

Others

PR changes

Others

Description

Add FLAGS_enable_fused_ffn_qkv_v2 for llama

@CLAassistant
Copy link
Copy Markdown

CLAassistant commented Sep 23, 2024

CLA assistant check
All committers have signed the CLA.

@codecov
Copy link
Copy Markdown

codecov Bot commented Sep 23, 2024

Codecov Report

Attention: Patch coverage is 18.18182% with 9 lines in your changes missing coverage. Please review.

Project coverage is 53.06%. Comparing base (cd4e816) to head (300833e).
Report is 6 commits behind head on develop.

Current head 300833e differs from pull request most recent head 12b7ac8

Please upload reports for the commit 12b7ac8 to get more accurate results.

Files with missing lines Patch % Lines
paddlenlp/transformers/llama/modeling_auto.py 18.18% 9 Missing ⚠️
Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #9182   +/-   ##
========================================
  Coverage    53.06%   53.06%           
========================================
  Files          656      656           
  Lines       106147   106152    +5     
========================================
+ Hits         56324    56334   +10     
+ Misses       49823    49818    -5     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link
Copy Markdown
Collaborator

@zhiqiu zhiqiu left a comment

Choose a reason for hiding this comment

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

LGTM

@zhangbo9674 zhangbo9674 changed the title [AutoParallel] Add FLAGS_enable_fused_ffn_qkv_v2 for llama [AutoParallel] Add FLAGS_enable_fused_ffn_qkv_pass for llama Sep 25, 2024
Copy link
Copy Markdown
Contributor

@ZHUI ZHUI left a comment

Choose a reason for hiding this comment

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

LGTM

@ZHUI ZHUI merged commit 1ce2642 into PaddlePaddle:develop Sep 25, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants