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

Optimizing GPT performance in inference #906

Merged
merged 16 commits into from
Nov 24, 2022
Merged

Optimizing GPT performance in inference #906

merged 16 commits into from
Nov 24, 2022

Conversation

carryyu
Copy link
Contributor

@carryyu carryyu commented Nov 9, 2022

Optimizing GPT performance in inference

Remaining problem:

  1. Attention_mask's shape
  2. Unfinished_flag in the while op when eos_token_id is None, which will cause synchronize.

@carryyu
Copy link
Contributor Author

carryyu commented Nov 10, 2022 via email

GuoxiaWang
GuoxiaWang approved these changes Nov 18, 2022
View reviewed changes
Copy link
Collaborator

@GuoxiaWang GuoxiaWang left a comment

Choose a reason for hiding this comment

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

LGTM

ppfleetx/models/language_model/gpt/auto/auto_model.py Outdated Show resolved Hide resolved
@Liujie0926 Liujie0926 merged commit ca87d1d into PaddlePaddle:develop Nov 24, 2022
@carryyu carryyu mentioned this pull request Nov 28, 2022
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ZHUI ZHUI ZHUI left review comments

@MARD1NO MARD1NO MARD1NO left review comments

@heavengate heavengate heavengate approved these changes

@GuoxiaWang GuoxiaWang GuoxiaWang approved these changes

@zhaoyinglia zhaoyinglia Awaiting requested review from zhaoyinglia

@ForFishes ForFishes Awaiting requested review from ForFishes

@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.
6 participants
@carryyu @heavengate @ZHUI @GuoxiaWang @MARD1NO @Liujie0926