Update modeling_deepseek.py

modeling_deepseek.py

@@ -527,8 +527,8 @@ class DeepseekV3MoE(nn.Module):
         topk_idx, topk_weight = self.gate(hidden_states)
         hidden_states = hidden_states.view(-1, hidden_states.shape[-1])
         flat_topk_idx = topk_idx.view(-1)
-        if not self.training:
-            y = self.moe_infer(hidden_states, topk_idx, topk_weight).view(*orig_shape)
+        #if not self.training:
+        y = self.moe_infer(hidden_states, topk_idx, topk_weight).view(*orig_shape)
         if self.config.n_shared_experts is not None:
             y = y + self.shared_experts(identity)
         return y