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

support new flash_attn_interface #1392

Open
rgtjf opened this issue Jan 7, 2025 · 1 comment
Open

support new flash_attn_interface #1392

rgtjf opened this issue Jan 7, 2025 · 1 comment
Assignees
@cyanguwa

Comments

@rgtjf
Copy link

rgtjf commented Jan 7, 2025 •
edited
Loading

wget -P $python_path/flashattn_hopper https://github.com/Dao-AILab/flash-attention/blob/284e2c6e5beff017996d72de6e028b2dc605acf8/hopper/flash_attn_interface.py

new version https://github.com/Dao-AILab/flash-attention/blob/main/hopper/flash_attn_interface.py
@cyanguwa
Copy link
Collaborator

cyanguwa commented Jan 9, 2025

Hi @rgtjf, could you elaborate on your request please? Is there a specific change you'd like to see in Transformer Engine regarding flash-attn? At the moment, this is what we support from flash-attn v3.

@cyanguwa cyanguwa self-assigned this Jan 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@cyanguwa cyanguwa

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@cyanguwa @rgtjf