Skip to content

Fix attention_mask broadcasting for NPU compatibility #13451

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

Open
chang-zhijie wants to merge 3 commits into
base: main
Choose a base branch
from
+8 −2
Open

Fix attention_mask broadcasting for NPU compatibility #13451

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2dd19ed
Fix attention_mask broadcasting for NPU compatibility
chang-zhijie Apr 13, 2026
1f33dda
Merge branch 'main' into main
chang-zhijie Apr 13, 2026
a7505e2
Merge branch 'main' into main
chang-zhijie Apr 14, 2026
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
10 changes: 8 additions & 2 deletions src/diffusers/models/transformers/transformer_ernie_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,8 +127,14 @@ def apply_rotary_emb(x_in: torch.Tensor, freqs_cis: torch.Tensor) -> torch.Tenso
query, key = query.to(dtype), key.to(dtype)

# From [batch, seq_len] to [batch, 1, 1, seq_len] -> broadcast to [batch, heads, seq_len, seq_len]
if attention_mask is not None and attention_mask.ndim == 2:
attention_mask = attention_mask[:, None, None, :]
if attention_mask is not None:
if attention_mask.ndim == 2:
attention_mask = attention_mask[:, None, None, :]

if attention_mask.ndim == 4:
# NPU does not support automatic broadcasting for this type; the mask must be expanded.
if attention_mask.device.type == 'npu' and attention_mask.shape[1:3] == (1, 1):
attention_mask = attention_mask.expand(-1, attn.heads, query.shape[1], -1)

# Compute joint attention
hidden_states = dispatch_attention_fn(
Expand Down
Loading