-
-
Notifications
You must be signed in to change notification settings - Fork 39
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Should I use linear layers for the input and output of FlashAttention? #247
Labels
Comments
Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap. |
@chelxu the linear projections are already handled inside of the flash attention. You just pass it the inital token embedding and then after that you can use the mlp and then process that an N number of times. What are you trying to build! And, I suggest you join the agora discord for real-time support! |
Stale issue message |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I'm curious, do I have to use the linear layer respectively first before I input qkv to FlaskAttention? When I get the output from FlaskAttention, do I still need the linear layer?
I look forward to your reply! Thanks!
The text was updated successfully, but these errors were encountered: