dsv4.1: remaining model and runtime integration (#38798)

Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>

docs/docs/advanced_features/server_arguments.mdx

@@ -2436,6 +2436,12 @@ Combining `--enable-response-store` with `--disaggregation-mode=prefill` or `dec
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`None`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Type: int</td>
     </tr>
+    <tr>
+      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--cuda-graph-max-seq-len-prefill`</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Longest sequence a prefill CUDA graph replay admits; longer batches run eager prefill. Folds into `cuda_graph_config[prefill].max_seq_len`.</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`None`</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Type: int</td>
+    </tr>
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--cuda-graph-bs-decode`</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Explicit list of batch sizes to capture for the decode CUDA graph.</td>

docs/src/snippets/configs/deepseek-ai/deepseek-v4_1.jsx

@@ -369,7 +369,7 @@ export const config = {
         "--mem-fraction-static 0.8",
         "--speculative-algorithm DSPARK",
         "--speculative-dspark-block-size 5",
-        "--cuda-graph-max-bs 64",
+        "--cuda-graph-max-bs-decode 64",
         "--cuda-graph-backend-prefill breakable",
         "--cuda-graph-max-bs-prefill 4096",
         "--reasoning-parser auto",