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

"Myelin Error in MyelinGraphContext" occur while I try to run trt model #124

Open
zkccpro opened this issue Aug 22, 2022 · 0 comments
Open
Assignees
Labels
bug Something isn't working

Comments

@zkccpro
Copy link

zkccpro commented Aug 22, 2022

First, I test a mmdet demo on https://github.com/open-mmlab/mmdetection, and it works.
Then I convert the .pth model to .trt model use mmdet2trt, and it works as well.
But when I run .trt model use the method in readme.md, it has a ERROR as follow:
[TensorRT] ERROR: myelin/myelinGraphContext.h (26) - Myelin Error in MyelinGraphContext: 1 (myelinVersionMismatch : Compiled against cuBLAS 11.3.0.0 but running against cuBLAS 11.2.1.0. ) terminate called after throwing an instance of 'nvinfer1::MyelinError' what(): std::exception Aborted (core dumped)
My env are: CUDA11.2, cudnn8.0.4, TensorRT7.2.3.4, mmdet2.25.1.
Now my confusion is: why I run .trt model ocuurs ERROR while the .pth model works properly?

@zkccpro zkccpro added the bug Something isn't working label Aug 22, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants