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

Author: Fridge003

docs/advanced_features/server_arguments.md

@@ -462,7 +462,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
 | `--rl-on-policy-target` | The training system that SGLang needs to match for true on-policy. | `None` | `fsdp` |
 | `--enable-attn-tp-input-scattered` | Allow input of attention to be scattered when only using tensor parallelism, to reduce the computational load of operations such as qkv latent. | `False` | bool flag (set to enable) |
 | `--enable-nsa-prefill-context-parallel` | Enable context parallelism used in the long sequence prefill phase of DeepSeek v3.2. | `False` | bool flag (set to enable) |
-| `--nsa-prefill-cp-mode` | Token splitting mode for the prefill phase of DeepSeek v3.2 under context parallelism. Optional values: `in-seq-split` (default), `round-robin-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. | `in-seq-split` | `in-seq-split`, `round-robin-split` |
+| `--nsa-prefill-cp-mode` | 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. | `in-seq-split` | `in-seq-split`, `round-robin-split` |
 | `--enable-fused-qk-norm-rope` | Enable fused qk normalization and rope rotary embedding. | `False` | bool flag (set to enable) |
 | `--enable-precise-embedding-interpolation` | Enable corner alignment for resize of embeddings grid to ensure more accurate(but slower) evaluation of interpolated embedding values. | `False` | bool flag (set to enable) |
 

docs/basic_usage/deepseek_v32.md

@@ -306,7 +306,7 @@ DeepSeek-V3.2-Speciale:
 
 For context parallel in DeepSeek V3.2 model, we provide two different modes of splitting tokens, which can be controlled with argument `--nsa-prefill-cp-mode`.
 
-### In sequence splitting (default setting)
+### In sequence splitting
 
 The first mode can be enabled by `--nsa-prefill-cp-mode in-seq-split`. This mode implements context parallel for DSA by splitting the sequence uniformly between context parallel ranks. At attention stage, each cp rank computes the indexer results of sharded sequence, and collects the whole kv cache through all gather operator.
 
@@ -326,7 +326,7 @@ Example:
 python -m sglang.launch_server --model deepseek-ai/DeepSeek-V3.2-Exp  --tp 8 --ep 8 --dp 2 --enable-dp-attention --enable-nsa-prefill-context-parallel --nsa-prefill-cp-mode in-seq-split --max-running-requests 32
 ```
 
-### Round robin splitting
+### Round robin splitting (default setting)
 
 This mode can be enabled by specifying the parameter `--nsa-prefill-cp-mode round-robin-split`, which distributes tokens across ranks based on `token_idx % cp_size`.
 

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 @@ def add_cli_args(parser: argparse.ArgumentParser):
             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(