diff --git a/tensorrt_llm/_torch/models/modeling_deepseekv3.py b/tensorrt_llm/_torch/models/modeling_deepseekv3.py
index be6c20ec92e1..c49064bfe38c 100755
--- a/tensorrt_llm/_torch/models/modeling_deepseekv3.py
+++ b/tensorrt_llm/_torch/models/modeling_deepseekv3.py
@@ -831,6 +831,14 @@ def compute_routed_output(self, hidden_states, hidden_states_fp4,
                               all_rank_num_tokens, do_finalize):
         # max-throughput
         use_dp_padding = False
+        # Add DP padding on SM120 for context comm performance
+        # TODO: Move this model-agonostic part to MoE
+        if self.use_dp and self.mapping.tp_size > 1 and get_sm_version() == 120:
+            use_dp_padding = True
+            hidden_states = torch.nn.functional.pad(
+                hidden_states,
+                (0, 0, 0, max(all_rank_num_tokens) - hidden_states.shape[0]))
+
         router_logits = self.gate(hidden_states)
 
         routed_output = self.experts(