Skip to content
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.

Sign up for GitHub

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

Fix Alibi in the flex-attention blog post #1825

Open
wants to merge 1 commit into
base: site
Choose a base branch
from
Open

Fix Alibi in the flex-attention blog post #1825

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions _posts/2024-08-07-flexattention.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,7 +131,7 @@ Alibi is similar to relative positional encodings with one exception \- it has a
alibi_bias = generate_alibi_bias() # [num_heads]

def alibi(score, b, h, q_idx, kv_idx):
bias = alibi_bias[h] * (q_idx - kv_idx)
bias = alibi_bias[h] * (kv_idx - q_idx)
return score + bias
```

Expand Down Expand Up @@ -479,4 +479,4 @@ We want to highlight some prior work (and people) that have inspired FlexAttenti
- The Jax team's work on SplashAttention
- Philippe Tillet and Keren Zhou for helping us with Triton
- Ali Hassani for discussions on neighborhood attention
- Everybody who's complained about attention kernels not supporting their favorite attention variant :)
- Everybody who's complained about attention kernels not supporting their favorite attention variant :)