Spaces:

sanchit-gandhi
/

parler-tts-streaming

Running on Zero

Enable Flash Attention

by tsdocode - opened May 23, 2024

May 23, 2024

Hi there, I saw you mentioned in spaces that applying Flash Attention can make model faster 2x~4x, did you implement it yet?
I've tried implement Flash Attention based on MusicGen FlashAttention but this does not speedup any!

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