Speed comparison between implementation with Flash-Attention and Xformer

by le723z - opened Sep 3

Sep 3

Hi,

As the model originally support flash-attention, I was wondering how the encoding speed would vary with two different acceleration strategy?

Best

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

Tap or paste here to upload images

· Sign up or log in to comment