Skip to content

GitLab

Unverified Commit e41bf15c authored by Xerxes's avatar Xerxes Committed by GitHub
Browse files

[Chore]: qwen3-moe-type-hints-mistake (#19860) 


Co-authored-by: default avatarxinnan.hou <hxn02029096@alibaba-inc.com>
parent 5aa4a015
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/models/qwen3_moe.py
View file @ e41bf15c
...@@ -294,7 +294,7 @@ class Qwen3MoeDecoderLayer(nn.Module): ...@@ -294,7 +294,7 @@ class Qwen3MoeDecoderLayer(nn.Module):
positions: torch.Tensor, positions: torch.Tensor,
hidden_states: torch.Tensor, hidden_states: torch.Tensor,
residual: Optional[torch.Tensor], residual: Optional[torch.Tensor],
) -> torch.Tensor: ) -> tuple[torch.Tensor, torch.Tensor]:
# Self Attention # Self Attention
if residual is None: if residual is None:
residual = hidden_states residual = hidden_states
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment