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

[paddle-inference]support setting fully connected in multi-head attention static shape branch to int8 #39660

Merged
merged 4 commits into from
Mar 4, 2022
Merged

[paddle-inference]support setting fully connected in multi-head attention static shape branch to int8 #39660

merged 4 commits into from
Mar 4, 2022

Conversation

ceci3
Copy link
Contributor

@ceci3 ceci3 commented Feb 17, 2022 •
edited
Loading

PR types

Performance optimization

PR changes

Others

Describe

support setting fully connected in multi-head attention static shape branch to int8

@paddle-bot-old
Copy link

Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@paddle-bot-old
Copy link

Sorry to inform you that 39d071c's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.

@ceci3 ceci3 closed this Mar 3, 2022
@ceci3 ceci3 reopened this Mar 3, 2022
wanghaoshuang
wanghaoshuang approved these changes Mar 4, 2022
View reviewed changes
Copy link
Contributor

@wanghaoshuang wanghaoshuang left a comment

Choose a reason for hiding this comment

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

LGTM

@ceci3 ceci3 changed the title [paddle-inference]fix inference int8 [paddle-inference]support int8 in multi-head attention static shape Mar 4, 2022
@ceci3 ceci3 changed the title [paddle-inference]support int8 in multi-head attention static shape [paddle-inference]support setting fully connected in multi-head attention static shape branch to int8 Mar 4, 2022
Wangzheee
Wangzheee approved these changes Mar 4, 2022
View reviewed changes
Copy link
Contributor

@Wangzheee Wangzheee left a comment

Choose a reason for hiding this comment

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

good

@ceci3 ceci3 merged commit 8dbfc2a into PaddlePaddle:develop Mar 4, 2022
@ceci3 ceci3 deleted the fix_infer_int8 branch March 4, 2022 06:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@wanghaoshuang wanghaoshuang wanghaoshuang approved these changes

@Wangzheee Wangzheee Wangzheee approved these changes

@qingqing01 qingqing01 Awaiting requested review from qingqing01

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
@ceci3 @wanghaoshuang @Wangzheee