Skip to content

fix: npu_rms_norm does not support gamma=None, use all-ones tensor in… #14585

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
xucqX wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −5
Open

fix: npu_rms_norm does not support gamma=None, use all-ones tensor in… #14585

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
12 changes: 7 additions & 5 deletions src/diffusers/models/normalization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,11 +542,13 @@ def forward(self, hidden_states):
if is_torch_npu_available():
import torch_npu

if self.weight is not None:
# convert into half-precision if necessary
if self.weight.dtype in [torch.float16, torch.bfloat16]:
hidden_states = hidden_states.to(self.weight.dtype)
hidden_states = torch_npu.npu_rms_norm(hidden_states, self.weight, epsilon=self.eps)[0]
# npu_rms_norm does not support gamma=None, use all-ones tensor instead
weight = self.weight
if weight is None:
weight = torch.ones(self.dim, device=hidden_states.device, dtype=hidden_states.dtype)
if weight.dtype in [torch.float16, torch.bfloat16]:
hidden_states = hidden_states.to(weight.dtype)
hidden_states = torch_npu.npu_rms_norm(hidden_states, weight, epsilon=self.eps)[0]
if self.bias is not None:
hidden_states = hidden_states + self.bias
else:
Expand Down
Loading