Skip to content

Don't materialise the PRX attention mask #14677

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

Merged
yiyixuxu merged 1 commit into from
Sep 2, 2026
Merged

Don't materialise the PRX attention mask #14677

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
5 changes: 4 additions & 1 deletion src/diffusers/models/transformers/transformer_prx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,10 @@ def __call__(
ones_img = torch.ones((bs, l_img), dtype=torch.bool, device=device)
attention_mask = attention_mask.to(device=device, dtype=torch.bool)
joint_mask = torch.cat([attention_mask, ones_img], dim=-1)
attn_mask_tensor = joint_mask[:, None, None, :].expand(-1, attn.heads, l_img, -1)
# Every attention backend broadcasts the mask itself, so materialising
# [B, heads, L_img, L_all] only costs bandwidth: at batch 32, 1024 image tokens
# and 28 heads that is a 1.1 GiB mask read per block. Keep it broadcastable.
attn_mask_tensor = joint_mask[:, None, None, :]

# Apply attention using dispatch_attention_fn for backend support
# Reshape to match dispatch_attention_fn expectations: [B, L, H, D]
Expand Down
Loading