[Docs]: Fix Multi-User Port Allocation Conflicts (#3601)

Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
Co-authored-by: simveit <simp.veitner@gmail.com>

docs/backend/patch.py

@@ -1,4 +1,5 @@
 import os
+import weakref
 
 from sglang.utils import execute_shell_command, reserve_port
 
@@ -21,15 +22,29 @@ def patched_post_init(self):
 
 server_args_mod.ServerArgs.__post_init__ = patched_post_init
 
+process_socket_map = weakref.WeakKeyDictionary()
+
 
 def launch_server_cmd(command: str, host: str = "0.0.0.0", port: int = None):
+    """
+    Launch the server using the given command.
+    If no port is specified, a free port is reserved.
+    """
     if port is None:
-        port = reserve_port()
+        port, lock_socket = reserve_port(host)
+    else:
+        lock_socket = None
+
     extra_flags = (
         f"--max-running-requests {DEFAULT_MAX_RUNNING_REQUESTS} "
         f"--max-total-tokens {DEFAULT_MAX_TOTAL_TOKENS} "
         f"--disable-cuda-graph"
     )
+
     full_command = f"{command} --port {port} {extra_flags}"
     process = execute_shell_command(full_command)
+
+    if lock_socket is not None:
+        process_socket_map[process] = lock_socket
+
     return process, port