-
Notifications
You must be signed in to change notification settings - Fork 947
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
ggml_flip
or ggml_pad_reflect
?
#819
Comments
I don't have a good idea which option would be more useful, so whatever you think makes more sense - PR welcome |
I like |
I ask because I need a working version of this to proceed with tortoise so I'm going to have to integrate it into at least my local copy of ggml anyway. |
@balisujohn Please go on! :) |
Hello,
I have implemented a custom operation
ggml_pad_reflec_1d
on my ggml fork. This is required for Encodec.cpp.Should I upstream this operation? I would write a
ggml_pad_reflect
supporting 1D and 2D input, as in PyTorch's nn.ReflectionPad2dAlternatively, I was considering implementing a
ggml_flip
operation (PyTorch's flip). This would allow us to implement apad_reflect
operation directly in 'user space' using flipping instead of adding a quite niche operation (pad_reflect
) toggml
.What are your thoughts? @slaren @ggerganov
The text was updated successfully, but these errors were encountered: