Skip to content

GitLab

Commit 440222e9 authored by zhuwenwen's avatar zhuwenwen
Browse files

fix qwen3-next run error

parent b8f555af
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 2 deletions
vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py
View file @ 440222e9
...@@ -289,7 +289,6 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp): ...@@ -289,7 +289,6 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
topk_weights: torch.Tensor, topk_weights: torch.Tensor,
topk_ids: torch.Tensor, topk_ids: torch.Tensor,
use_nn_moe: bool | None = False, use_nn_moe: bool | None = False,
use_fused_gate: bool | None = False,
) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor]: ) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor]:
return self.forward( return self.forward(
layer=layer, layer=layer,
...@@ -297,7 +296,6 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp): ...@@ -297,7 +296,6 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
topk_weights=topk_weights, topk_weights=topk_weights,
topk_ids=topk_ids, topk_ids=topk_ids,
use_nn_moe=use_nn_moe, use_nn_moe=use_nn_moe,
use_fused_gate=use_fused_gate,
) )
def get_fused_moe_quant_config(self, layer: torch.nn.Module) -> FusedMoEQuantConfig: def get_fused_moe_quant_config(self, layer: torch.nn.Module) -> FusedMoEQuantConfig:
......
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