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

量化我的onnx文件时出现,AttributeError: FLOAT8E4M3FN #16

Closed
scuizhibin opened this issue Jul 1, 2024 · 3 comments
Closed

Comments

@scuizhibin
Copy link

环境版本
onnx 1.13.0
onnx-graphsurgeon 0.3.12
onnxruntime 1.18.0
onnxslim 0.1.29
numpy 1.21.0

bevformer.zip

@inisis
Copy link
Owner

inisis commented Jul 1, 2024

This is a compatiblity problem, please upgrade your onnx version to 1.16.

@scuizhibin
Copy link
Author

bevformerencodertrt.zip
这个是优化前的onnx,使用tensorrt8.5.2量化是没有问题的,但是使用onnxslim优化过后 就会出现问题 operation.cpp:203: DCHECK(!i->is_use_only()) failed.

@scuizhibin
Copy link
Author

这个是TENSORRT版本问题,降低版本就行使用8.4。

@inisis inisis closed this as completed Jul 29, 2024
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

No branches or pull requests

2 participants