|
What is the ratio between query heads and key-value heads in GQA? |
Answered by
Ultron09
Aug 28, 2026
Replies: 1 comment
|
GQA groups G query heads to share a single key-value head, reducing memory bandwidth by Gx with minimal quality degradation. |
0 replies
Answer selected by
Ultron09
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
GQA groups G query heads to share a single key-value head, reducing memory bandwidth by Gx with minimal quality degradation.