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 9426843 commit 2250446Copy full SHA for 2250446
vllm/model_executor/layers/fused_moe/layer.py
@@ -936,7 +936,9 @@ def forward_xpu(
936
return xpu_fused_moe(
937
hidden_states=x,
938
w13=layer.w13_weight,
939
+ w13_bias=layer.w13_bias if self.moe.has_bias else None,
940
w2=layer.w2_weight,
941
+ w2_bias=layer.w2_bias if self.moe.has_bias else None,
942
topk_weights=routing_weights,
943
topk_ids=selected_experts,
944
n_experts_per_token=top_k,
0 commit comments