[V3.2] Change default CP token split method to --round-robin-split (#18613)

python/sglang/srt/server_args.py

@@ -628,7 +628,7 @@ class ServerArgs:
     enable_attn_tp_input_scattered: bool = False
     # Context parallelism used in the long sequence prefill phase of DeepSeek v3.2
     enable_nsa_prefill_context_parallel: bool = False
-    nsa_prefill_cp_mode: str = "in-seq-split"
+    nsa_prefill_cp_mode: str = "round-robin-split"
     enable_fused_qk_norm_rope: bool = False
     enable_precise_embedding_interpolation: bool = False
 
@@ -4684,7 +4684,7 @@ class ServerArgs:
             type=str,
             default=ServerArgs.nsa_prefill_cp_mode,
             choices=NSA_PREFILL_CP_SPLIT_CHOICES,
-            help="Token splitting mode for the prefill phase of DeepSeek v3.2 under context parallelism. Optional values: 'in-seq-split' (default), 'round-robin-split'. "
+            help="Token splitting mode for the prefill phase of DeepSeek v3.2 under context parallelism. Optional values: 'round-robin-split'(default), 'in-seq-split'  "
             "'round-robin-split' distributes tokens across ranks based on token_idx %% cp_size. It supports multi-batch prefill, fused MoE, and FP8 KV cache.",
         )
         parser.add_argument(