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

Dynamic shape compilation support for flex attention with block mask #33

Open
SamGalanakis opened this issue Aug 28, 2024 · 1 comment
Open

Dynamic shape compilation support for flex attention with block mask #33

SamGalanakis opened this issue Aug 28, 2024 · 1 comment

Comments

@SamGalanakis
Copy link

Repro here: pytorch/pytorch#134560
It is mentioned in the original flex attention blog that dynamic shapes work should I be implementing it differently? My usecase is for document packing so varying batch size, block mask is recomputed at each step. Blocked by this for switching to flex attention unfortunately, thanks in advance.
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
@SamGalanakis and others