[Question] 请问7B没有用上FlashAttention吗？ - Githubissues

baichuan-inc / Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

https://huggingface.co/baichuan-inc/baichuan-7B

Apache License 2.0

5.67k stars 507 forks source link

[Question] 请问7B没有用上FlashAttention吗？ #130

Open nezhazheng opened 1 year ago

nezhazheng commented 1 year ago

Required prerequisites

[X] I have read the documentation https://github.com/baichuan-inc/baichuan-7B/blob/HEAD/README.md.
[X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
[X] Consider asking first in a Discussion.

Questions

请问7B没有用上FlashAttention吗？看了下7B代码，没发现这块的逻辑。

Checklist

[X] I have provided all relevant and necessary information above.
[X] I have chosen a suitable title for this issue.

mmmans commented 1 year ago

No. We user xformers for training, and naive impl for inference.