flash-attention icon indicating copy to clipboard operation
flash-attention copied to clipboard

Published 20 hours ago • verified publisher icon Dao-AILab

support for Quadro RTX 8000?

Open Crazy-LittleBoy opened this issue 2 years ago • 5 comments
trafficstars

flash attention 1 support turing, but flash attention 2 not ?

Crazy-LittleBoy avatar Sep 21 '23 05:09 Crazy-LittleBoy

Yup, it's mentioned in the README

FlashAttention-2 currently supports:

Ampere, Ada, or Hopper GPUs (e.g., A100, RTX 3090, RTX 4090, H100). Support for Turing GPUs (T4, RTX 2080) is coming soon, please use FlashAttention 1.x for Turing GPUs for now.

tridao avatar Sep 21 '23 05:09 tridao

Support for Turing GPUs (T4, RTX 2080) is coming soon. Looking forward to it. @tridao

chuanzhubin avatar Apr 07 '24 02:04 chuanzhubin

Unfortunately I've had no bandwidth to work on this. We welcome contributions.

tridao avatar Apr 07 '24 03:04 tridao