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.

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

modify block_multihead_attention api #8456

Merged
merged 5 commits into from
May 28, 2024

Conversation

ming1753
Copy link
Contributor

@ming1753 ming1753 commented May 16, 2024

PR types

Others

PR changes

Others

Description

PaddlePaddle/Paddle#64246
Paddledevelop修改了block_multihead_attention,该PR与之对齐。
blha算子新增两个可选参数max_enc_len_this_time和max_dec_len_this_time,在传入时不在kernel内部计算,推理性能提升10%+。

Copy link

paddle-bot bot commented May 16, 2024

Thanks for your contribution!

Copy link

codecov bot commented May 16, 2024

Codecov Report

Attention: Patch coverage is 0% with 5 lines in your changes are missing coverage. Please review.

Project coverage is 54.27%. Comparing base (87e4c4f) to head (7634b64).
Report is 3 commits behind head on develop.

Current head 7634b64 differs from pull request most recent head 11c122e

Please upload reports for the commit 11c122e to get more accurate results.

Files Patch % Lines
...erimental/transformers/fused_transformer_layers.py 0.00% 5 Missing ⚠️
Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #8456      +/-   ##
===========================================
- Coverage    54.29%   54.27%   -0.03%     
===========================================
  Files          617      617              
  Lines        96339    96361      +22     
===========================================
- Hits         52312    52304       -8     
- Misses       44027    44057      +30     

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

Copy link
Collaborator

@wawltor wawltor left a comment

Choose a reason for hiding this comment

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

LGTM

@wawltor wawltor merged commit c1cfe63 into PaddlePaddle:develop May 28, 2024
8 of 10 checks passed
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.

2 participants