[Question] Why delete q_b_scale kv_b_scale k_b_trans_scale #2970

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

Open

nanmi opened this issue Mar 21, 2025 · 0 comments

Labels

not a bug

nanmi commented Mar 21, 2025

Why did the gpt_attention function delete the parameters

q_b_scale: Optional[Tensor] = None,
kv_b_scale: Optional[Tensor] = None,
k_b_trans_scale: Optional[Tensor] = None,

and is_fp8_model_flag in the latest code?
Can anyone explain the reason?

The text was updated successfully, but these errors were encountered:

dominicshanshan added the not a bug label

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