[DCP] Auto-disable tc_piecewise and breakable prefill CUDA graphs under DCP (#31532)

Co-authored-by: Cursor <cursoragent@cursor.com>

python/sglang/srt/server_args.py

@@ -3651,6 +3651,11 @@ class ServerArgs:
                 "DSA prefill context parallelism",
                 lambda: self.enable_dsa_prefill_context_parallel,
             ),
+            # Capture builds a dummy extend forward with attn_dcp_metadata=None.
+            (
+                "decode context parallel (dcp_size > 1)",
+                lambda: self.dcp_size > 1,
+            ),
         ]
         for _name, predicate in rules:
             if predicate():
@@ -3679,6 +3684,11 @@ class ServerArgs:
                 "context parallel (attn_cp_size > 1)",
                 lambda: self._resolved().attn_cp_size > 1,
             ),
+            # Capture builds a dummy extend forward with attn_dcp_metadata=None.
+            (
+                "decode context parallel (dcp_size > 1)",
+                lambda: self.dcp_size > 1,
+            ),
             # BCG capture + LoRA adapter weights exceed host RAM headroom.
             ("LoRA", lambda: bool(self.lora_paths) or bool(self.enable_lora)),
             # BCG bucket sizes exceed FlashInfer MoE A2A's dispatch cap.