Skip to content

perf: avoid graph break for SiLUT when inferring #4790

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

Merged
iProzd merged 1 commit into from
Jun 10, 2025
Merged

perf: avoid graph break for SiLUT when inferring #4790

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
11 changes: 4 additions & 7 deletions deepmd/pt/utils/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,13 +149,10 @@ def silu_grad(x):
self.const = float(silu(threshold))

def forward(self, x: torch.Tensor) -> torch.Tensor:
silu_part = F.silu(x)
mask = x >= self.threshold
if torch.any(mask):
tanh_part = torch.tanh(self.slope * (x - self.threshold)) + self.const
return torch.where(x < self.threshold, silu_part, tanh_part)
else:
return silu_part
sig = torch.sigmoid(x)
silu = x * sig
tanh = torch.tanh(self.slope * (x - self.threshold)) + self.const
return torch.where(x >= self.threshold, tanh, silu)


class ActivationFn(torch.nn.Module):
Expand Down
Loading