Flash Attention 2

by Modularity - opened Jul 5, 2024

Jul 5, 2024

The model does not have the support for Flash Attention 2.0, which makes it not practical

czczup

OpenGVLab org Jul 7, 2024

Thanks for your feedback, flash attention is now supported.

czczup changed discussion status to closed Jul 11, 2024

Jul 18, 2024

Is it possible to switch to Flash Attention 1.0 or disable it all together?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment