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

Fix sampling decoding when model without parallel #2561

Merged
merged 3 commits into from
Jun 17, 2022

Conversation

gongel
Copy link
Member

@gongel gongel commented Jun 17, 2022

PR types

Bug fixes

PR changes

Others

Description

  • 问题:不支持并行推理的模型 sampling decoding时会报Segmentation fault (core dumped)错误
  • 解决:不支持并行推理的模型l_parallel_param_.layers_per_group(默认值为0)应该等于模型层数。

@gongel gongel changed the title Fix model's sampling without parallel Fix sampling decoding when model without parallel Jun 17, 2022
Copy link
Collaborator

@guoshengCS guoshengCS left a comment

Choose a reason for hiding this comment

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

LGTM

@gongel gongel merged commit 5901915 into PaddlePaddle:develop Jun 17, 2022
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.

None yet

3 participants