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

torch2trt build broken #502

Closed
hslr4 opened this issue May 7, 2024 · 3 comments
Closed

torch2trt build broken #502

hslr4 opened this issue May 7, 2024 · 3 comments

Comments

@hslr4
Copy link

hslr4 commented May 7, 2024

The torch2trt build fails since an update of torch2trt that removed torch2trt/converters/interpolate.py.

It seems to work again when lines 15 and 16 are removed from the corresponding Dockerfile here:

sed 's|collections.Sequence|collections.abc.Sequence|g' -i torch2trt/converters/interpolate.py && \

Apperantly the problem this sed command fixed, is fixed in torch2trt itself since a previous commit: NVIDIA-AI-IOT/torch2trt@f0520f0#diff-f34a4426e314e2b5c6097e416ede5acbe4abde50448ef570a2999783969c5189

@dusty-nv
Copy link
Owner

dusty-nv commented May 7, 2024

Thanks @hslr4, yes I am getting JP6 GA / L4T R35.3 setup now and will update the dockerfile for latest torch2trt 👍

@dusty-nv
Copy link
Owner

dusty-nv commented May 7, 2024

OK, this is fixed now in d5bc44e

@hslr4
Copy link
Author

hslr4 commented May 27, 2024

thanks 👍

@hslr4 hslr4 closed this as completed May 27, 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