Skip to content

ROPE computing suitable for NPU #12836

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
leisuzz wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −3
Open

ROPE computing suitable for NPU #12836

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
15 changes: 12 additions & 3 deletions src/diffusers/models/embeddings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1169,9 +1169,18 @@ def get_1d_rotary_pos_embed(
if is_npu:
freqs = freqs.float()
if use_real and repeat_interleave_real:
# flux, hunyuan-dit, cogvideox
freqs_cos = freqs.cos().repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).float() # [S, D]
freqs_sin = freqs.sin().repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).float() # [S, D]
if is_npu:
# flux, hunyuan-dit, cogvideox that suitable for NPU
freqs_cos = (
freqs.cos().T.repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).T.float().contiguous()
) # [S, D]
freqs_sin = (
freqs.sin().T.repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).T.float().contiguous()
) # [S, D]
else:
# flux, hunyuan-dit, cogvideox
freqs_cos = freqs.cos().repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).float() # [S, D]
freqs_sin = freqs.sin().repeat_interleave(2, dim=1, output_size=freqs.shape[1] * 2).float() # [S, D]
return freqs_cos, freqs_sin
elif use_real:
# stable audio, allegro
Expand Down