Skip to content
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

step by step study FlashMLA, what does fixed_overhead_num_blocks mean? #38

Open
defei-coder opened this issue Feb 25, 2025 · 2 comments
Open

step by step study FlashMLA, what does fixed_overhead_num_blocks mean? #38

defei-coder opened this issue Feb 25, 2025 · 2 comments

Comments

@defei-coder
Copy link

No description provided.

@defei-coder
Copy link
Author

@beginlner Hi，fixed_overhead_num_blocks is used for sm occupy？I confused this parameters.

@beginlner
Copy link
Collaborator

beginlner commented Feb 26, 2025 •
edited
Loading

Here we assume that the computation time of a tile is fixed_overhead_num_blocks + ceil(seqlen / num_blocks). fixed_overhead_num_blocks is an estimation of cool start & drain overhead.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@beginlner @defei-coder