diff --git a/python/sglang/srt/models/deepseek_nextn.py b/python/sglang/srt/models/deepseek_nextn.py
index c0d135f50..21ded56d7 100644
--- a/python/sglang/srt/models/deepseek_nextn.py
+++ b/python/sglang/srt/models/deepseek_nextn.py
@@ -179,8 +179,9 @@ class DeepseekModelNextN(nn.Module):
         use_cp = nsa_use_prefill_cp(forward_batch, self.nsa_enable_prefill_cp)
         use_cp_local_draft = use_cp and envs.SGLANG_CP_DRAFT_SHARED_KV.get()
         if use_cp_local_draft:
-            local_input_ids = cp_split_and_rebuild_1d(forward_batch, input_ids)
-            local_num_tokens = local_input_ids.shape[0]
+            local_num_tokens = cp_split_and_rebuild_1d(
+                forward_batch, input_ids
+            ).shape[0]
             local_positions = cp_split_and_rebuild_position(forward_batch, positions)
             spec_hidden_states = self._get_cp_local_spec_hidden_states(
                 forward_batch,
@@ -193,7 +194,11 @@ class DeepseekModelNextN(nn.Module):
             else:
                 positions = local_positions
                 if input_embeds is None:
-                    hidden_states = self.embed_tokens(local_input_ids)
+                    # Embed full input first so all ranks see the same tensor
+                    # shape in the TP all-reduce, then CP-split the result.
+                    hidden_states = cp_split_and_rebuild_data(
+                        forward_batch, self.embed_tokens(input_ids)
+                    )
                 elif input_embeds.shape[0] == local_num_tokens:
                     hidden_states = input_embeds
                 elif input_embeds.shape[0] == input_ids.shape[0]: