diff --git a/docs/basic_usage/deepseek_v32.md b/docs/basic_usage/deepseek_v32.md
index 56f37f29c..4894954e7 100644
--- a/docs/basic_usage/deepseek_v32.md
+++ b/docs/basic_usage/deepseek_v32.md
@@ -316,8 +316,7 @@ The first mode can be enabled by `--nsa-prefill-cp-mode in-seq-split`. This mode
 
 Note that in sequence splitting mode has the following restrictions:
 - The batch size is restricted to 1 for prefill batches
-- Multi-node/PD disaggregation is still not supported
-- `moe_dense_tp_size=1`, `kv_cache_dtype = "bf16"`, `moe_a2a_backend = "deepep"`
+- `moe_dense_tp_size=1`, `moe_a2a_backend = "deepep"`
 - To ensure `cp_size > 1`, the passed in `tp_size` must be larger than `dp_size`
 
 For more details, please refer to PR https://github.com/sgl-project/sglang/pull/12065.
diff --git a/python/sglang/srt/layers/attention/nsa/utils.py b/python/sglang/srt/layers/attention/nsa/utils.py
index 00ef96f9b..8b17c574c 100644
--- a/python/sglang/srt/layers/attention/nsa/utils.py
+++ b/python/sglang/srt/layers/attention/nsa/utils.py
@@ -54,7 +54,7 @@ def can_nsa_prefill_cp_round_robin_split(forward_batch: "ForwardBatch"):
         return False
     cp_size = get_attention_cp_size()
     seq_len = sum(forward_batch.extend_seq_lens_cpu)
-    return is_nsa_prefill_cp_round_robin_split() and seq_len > 0 and cp_size > 1
+    return is_nsa_prefill_cp_round_robin_split() and seq_len > 0 and seq_len >= cp_size and cp_size > 1
 
 
 def nsa_cp_round_robin_split_data(input_: Union[torch.Tensor, List]):
@@ -167,6 +167,7 @@ def can_cp_split(seq_len: int, cp_size: int, use_nsa: bool, forward_batch):
         and use_nsa
         and forward_batch.forward_mode.is_context_parallel_extend()
         and is_nsa_enable_prefill_cp()
+        and sum(forward_batch.extend_seq_lens_cpu) >= cp_size
     ):
         return True
     else:
diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
index 5e04f3db9..02ee4c6b7 100644
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1302,9 +1302,8 @@ class ServerArgs:
                             self.moe_dense_tp_size = 1
                             self.moe_a2a_backend = "deepep"
                             self.ep_size = self.tp_size
-                            self.kv_cache_dtype = "bf16"
                             logger.warning(
-                                "For in-seq split mode, we have the following restrictions: moe_dense_tp_size == 1, moe_a2a_backend == deepep, ep_size == tp_size, kv_cache_dtype == bf16, batch_size == 1"
+                                "For in-seq split mode, we have the following restrictions: moe_dense_tp_size == 1, moe_a2a_backend == deepep, ep_size == tp_size, batch_size == 1"
                             )
                         else:
                             self.enable_dp_attention = True