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

Inconsistent inference accuracy of pytorch model caused by cuda version #283

Open

zhangchen98 opened this issue Jul 16, 2024 · 0 comments

zhangchen98 commented Jul 16, 2024

When I use the gpu version of pytorch for model inference, I found that the output tensor accuracy is inconsistent, as follows:

When I switch to cpu, this problem does not occur. Furthermore, I can also get consistent results when using lower cuda versions (11.6->11.3).

Environment:

pytorch: 1.12
linux

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