Skip to content

Perform in-place zeroing instead of creating new tensors #13037

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
AkashKarnatak wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −4
Open

Perform in-place zeroing instead of creating new tensors #13037

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
6 changes: 2 additions & 4 deletions src/diffusers/pipelines/wan/pipeline_wan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,10 +184,8 @@ def _get_t5_prompt_embeds(

prompt_embeds = self.text_encoder(text_input_ids.to(device), mask.to(device)).last_hidden_state
prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
prompt_embeds = [u[:v] for u, v in zip(prompt_embeds, seq_lens)]
prompt_embeds = torch.stack(
[torch.cat([u, u.new_zeros(max_sequence_length - u.size(0), u.size(1))]) for u in prompt_embeds], dim=0
)
for i, seq_len in enumerate(seq_lens):
prompt_embeds[i, seq_len:] = 0

# duplicate text embeddings for each generation per prompt, using mps friendly method
_, seq_len, _ = prompt_embeds.shape
Expand Down