Support v1/responses and use harmony in serving_chat (#8837)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

python/sglang/srt/server_args.py

@@ -274,6 +274,9 @@ class ServerArgs:
     enable_pdmux: bool = False
     sm_group_num: int = 3
 
+    # For tool server
+    tool_server: Optional[str] = None
+
     # Deprecated arguments
     enable_ep_moe: bool = False
     enable_deepep_moe: bool = False
@@ -1916,6 +1919,14 @@ class ServerArgs:
             help="Disable mmap while loading weight using safetensors.",
         )
 
+        # For tool server
+        parser.add_argument(
+            "--tool-server",
+            type=str,
+            default=None,
+            help="Either 'demo' or a comma-separated list of tool server urls to use for the model. If not specified, no tool server will be used.",
+        )
+
         # Deprecated arguments
         parser.add_argument(
             "--enable-ep-moe",