diff --git a/python/sglang/srt/models/glm4_moe.py b/python/sglang/srt/models/glm4_moe.py
index 0c1e1d000..c7bbffe81 100644
--- a/python/sglang/srt/models/glm4_moe.py
+++ b/python/sglang/srt/models/glm4_moe.py
@@ -415,6 +415,7 @@ class Glm4MoeSparseMoeBlock(nn.Module):
                     if get_moe_a2a_backend().is_deepep()
                     or get_moe_a2a_backend().is_mooncake()
                     or get_moe_a2a_backend().is_flashinfer()
+                    or get_moe_a2a_backend().is_megamoe()
                     or should_use_flashinfer_cutlass_moe_fp4_allgather()
                     else {}
                 ),
@@ -463,6 +464,13 @@ class Glm4MoeSparseMoeBlock(nn.Module):
         should_allreduce_fusion: bool = False,
         use_reduce_scatter: bool = False,
     ) -> torch.Tensor:
+        from sglang.srt.layers.moe.mega_moe import (
+            forward_mega_moe,
+            should_use_mega_moe,
+        )
+
+        if should_use_mega_moe(self, hidden_states):
+            return forward_mega_moe(self, hidden_states, forward_batch)
 
         if not get_moe_a2a_backend().is_deepep():
             if (