add greedy

modeling_deepseek.py

@@ -461,6 +461,10 @@ class MoEGate(nn.Module):
                 tmp_scores, k=self.top_k, dim=-1, sorted=False
             )
             topk_weight = scores.gather(1, topk_idx)
+        elif self.topk_method == "greedy":
+            topk_weight, topk_idx = torch.topk(
+                scores, k=self.top_k, dim=-1, sorted=False
+            )
         else:
             raise NotImplementedError(
                 f"insupportable TopK function for MoE gating: {self.topk_method}"