Skip to content

use pytorch built-in SiLU function to save GPU memory usage #331

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

use pytorch built-in SiLU function to save GPU memory usage #331

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
3 changes: 2 additions & 1 deletion ldm/modules/diffusionmodules/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
import numpy as np
from einops import rearrange
from typing import Optional, Any
import torch.nn.functional as F

from ldm.modules.attention import MemoryEfficientCrossAttention

Expand Down Expand Up @@ -40,7 +41,7 @@ def get_timestep_embedding(timesteps, embedding_dim):

def nonlinearity(x):
# swish
return x*torch.sigmoid(x)
return F.silu(x)


def Normalize(in_channels, num_groups=32):
Expand Down