-
Notifications
You must be signed in to change notification settings - Fork 200
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
Why is the implementation of Mamba so slow? #21
Comments
I am also facing the similar issue. Are you able to find the reason for it? |
that is mainly because there is something wrong which lead the loss.backward so slow |
It's not meant to be fast! This repo is mostly only for educational purposes. I would suggest using the official repo to do any training: https://github.com/state-spaces/mamba |
probably because mamba-ssm designed a GPU-adapted scanning operation based on C. |
I think the problem is embeding layer. D-layer is 50280, lol. |
I haven't run the official version of Mamba, but I've run your implementation, and it seems that the training speed of this model is much slower than that of the Transformer.
The text was updated successfully, but these errors were encountered: