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.

Sign up for GitHub

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

Jump to bottom

Problem of Selective SSM Implementation #685

Open

JianKai0716 opened this issue Feb 4, 2025 · 0 comments

JianKai0716 commented Feb 4, 2025 •

edited

Loading

Hi,

I have some problems with the details of selective ssm in mamba_simple.py.

Because there are errors when run code in line 241-244, I want to check the problem as follows:

In the line of 241, dA = torch.exp(torch.einsum("bd,dn->bdn", dt, A)).

I am not sure the dA is derived from matrix multiplication or elementwise multiplication of dt and A?

Also, the same confusion with the way we obtain dB, ssm_state, and y in line 242, 243, and 244, respectively.

I hope someone can help me clear up my confusion. I would be extremely grateful.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment