Skip to content

[core] make flux hidden states contiguous #13068

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
sayakpaul wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[core] make flux hidden states contiguous #13068

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
23fdf38
make flux hidden states contiguous
sayakpaul Feb 3, 2026
82aaa36
make fix-copies
sayakpaul Feb 3, 2026
fcdfaf0
Merge branch 'main' into flux-contiguous
sayakpaul Feb 4, 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
4 changes: 2 additions & 2 deletions src/diffusers/models/transformers/transformer_bria_fibo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,9 +125,9 @@ def __call__(
encoder_hidden_states, hidden_states = hidden_states.split_with_sizes(
[encoder_hidden_states.shape[1], hidden_states.shape[1] - encoder_hidden_states.shape[1]], dim=1
)
hidden_states = attn.to_out[0](hidden_states)
hidden_states = attn.to_out[0](hidden_states.contiguous())
hidden_states = attn.to_out[1](hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states.contiguous())

return hidden_states, encoder_hidden_states
else:
Expand Down
4 changes: 2 additions & 2 deletions src/diffusers/models/transformers/transformer_flux.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,9 +130,9 @@ def __call__(
encoder_hidden_states, hidden_states = hidden_states.split_with_sizes(
[encoder_hidden_states.shape[1], hidden_states.shape[1] - encoder_hidden_states.shape[1]], dim=1
)
hidden_states = attn.to_out[0](hidden_states)
hidden_states = attn.to_out[0](hidden_states.contiguous())
hidden_states = attn.to_out[1](hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states.contiguous())
Comment on lines +133 to +135
Copy link

Copilot AI Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The same contiguous() fix should be applied to the FluxIPAdapterAttnProcessor class. Lines 240-242 have an identical split_with_sizes pattern but are missing the contiguous() calls. For consistency and to ensure NVFP4 quantization benefits are available across all attention processors, please add contiguous() calls at lines 240 and 242 similar to these changes.

Copilot uses AI. Check for mistakes.

return hidden_states, encoder_hidden_states
else:
Expand Down
Loading