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

相同模型在A100机器和海光DCU机器上使用“from paddle.fluid.core import create_paddle_predictor”时会导致效果有差异 #68217

Open
SpoongeTBob opened this issue Sep 13, 2024 · 1 comment
Open

相同模型在A100机器和海光DCU机器上使用“from paddle.fluid.core import create_paddle_predictor”时会导致效果有差异 #68217

SpoongeTBob opened this issue Sep 13, 2024 · 1 comment
Assignees
@gongel
Labels
status/new-issue 新建 type/bug-report 报bug

Comments

@SpoongeTBob
Copy link

bug描述 Describe the Bug

python版本 3.8
paddle 2.4

其他补充信息 Additional Supplementary Information

No response
@SpoongeTBob SpoongeTBob changed the title 相同模型在A100机器和海光机器上使用“from paddle.fluid.core import create_paddle_predictor”时会导致效果有差异 相同模型在A100机器和海光DCU机器上使用“from paddle.fluid.core import create_paddle_predictor”时会导致效果有差异 Sep 13, 2024
@SpoongeTBob
Copy link
Author

在相同代码和模型文件情况下,A100硬件设备处理数据效果稳定,dcu设备处理返回结果与A100设备有偏差,并且每次返回结果不同,排查为paddle算子内的问题.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@gongel gongel

Labels
status/new-issue 新建 type/bug-report 报bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@gongel @SpoongeTBob