We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f6f4e71 commit 376ce81Copy full SHA for 376ce81
vllm/model_executor/models/qwen3_moe.py
@@ -294,7 +294,7 @@ def forward(
294
positions: torch.Tensor,
295
hidden_states: torch.Tensor,
296
residual: Optional[torch.Tensor],
297
- ) -> torch.Tensor:
+ ) -> tuple[torch.Tensor, torch.Tensor]:
298
# Self Attention
299
if residual is None:
300
residual = hidden_states
0 commit comments