We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
No description provided.
The text was updated successfully, but these errors were encountered:
@Zeqiang-Lai What do you mean by kv to be constant? Can you show an example?
Sorry, something went wrong.
I have a network that calls a cross attention multiple times with different queries but the same k, v.
k, v = ... for chunk_q in q: attention(chunk_q,k,v)
I think the speed can be faster (quantize k and v only once) but the accuracy cannot be improved.
No branches or pull requests
No description provided.
The text was updated successfully, but these errors were encountered: