Skip to content

diffusion: fix LoRA dtype handling and weight attribute access for z-image model #14543

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
mickqian merged 2 commits into from
Dec 6, 2025
Merged

diffusion: fix LoRA dtype handling and weight attribute access for z-image model #14543

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1dcbffe
fix: z-image get weigth and output tensor dtype error
Dec 6, 2025
934984b
fix: lint error
Dec 6, 2025
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
10 changes: 9 additions & 1 deletion python/sglang/multimodal_gen/runtime/layers/lora/linear.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,14 @@ def __init__(
self.lora_A = None
self.lora_B = None

@property
def weight(self):
return self.base_layer.weight

@property
def bias(self):
return getattr(self.base_layer, "bias", None)

@torch.compile()
def forward(self, x: torch.Tensor) -> torch.Tensor:
lora_A = self.lora_A
Expand All @@ -79,7 +87,7 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
return out + delta, output_bias
else:
out, output_bias = self.base_layer(x)
return out.to(x), output_bias
return out, output_bias
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The method returns a tuple (out, output_bias), but the return type hint for the forward method on line 71 is torch.Tensor. This should be updated to tuple[torch.Tensor, torch.Tensor | None] to match the actual return type. This will improve type safety and code clarity.


def slice_lora_a_weights(self, A: torch.Tensor) -> torch.Tensor:
return A
Expand Down
Loading