[Feature]TP Group Switching for PD-Multiplexing (#7653)

python/sglang/srt/server_args.py

@@ -251,6 +251,10 @@ class ServerArgs:
     custom_weight_loader: Optional[List[str]] = None
     weight_loader_disable_mmap: bool = False
 
+    # For PD-Multiplexing
+    enable_pdmux: bool = False
+    sm_group_num: int = 3
+
     def __post_init__(self):
         # Expert parallelism
         if self.enable_ep_moe:
@@ -1721,6 +1725,17 @@ class ServerArgs:
             default=None,
             help="The custom dataloader which used to update the model. Should be set with a valid import path, such as my_package.weight_load_func",
         )
+        parser.add_argument(
+            "--enable-pdmux",
+            action="store_true",
+            help="Enable PD-Multiplexing, PD running on greenctx stream.",
+        )
+        parser.add_argument(
+            "--sm-group-num",
+            type=int,
+            default=ServerArgs.sm_group_num,
+            help="Number of sm partition groups.",
+        )
         parser.add_argument(
             "--weight-loader-disable-mmap",
             action="store_true",