[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/function_calling.ipynb

@@ -405,7 +405,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(server_process, port)"
+    "terminate_process(server_process)"
    ]
   },
   {

docs/backend/native_api.ipynb

@@ -252,7 +252,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(server_process, port)\n",
+    "terminate_process(server_process)\n",
     "\n",
     "embedding_process, port = launch_server_cmd(\n",
     "    \"\"\"\n",
@@ -286,7 +286,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(embedding_process, port)"
+    "terminate_process(embedding_process)"
    ]
   },
   {
@@ -304,7 +304,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(embedding_process, port)\n",
+    "terminate_process(embedding_process)\n",
     "\n",
     "# Note that SGLang now treats embedding models and reward models as the same type of models.\n",
     "# This will be updated in the future.\n",
@@ -355,7 +355,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(reward_process, port)"
+    "terminate_process(reward_process)"
    ]
   },
   {
@@ -425,7 +425,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(tokenizer_free_server_process, port)"
+    "terminate_process(tokenizer_free_server_process)"
    ]
   }
  ],

docs/backend/openai_api_completions.ipynb

@@ -512,7 +512,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(server_process, port)"
+    "terminate_process(server_process)"
    ]
   }
  ],

docs/backend/openai_api_embeddings.ipynb

@@ -169,7 +169,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(embedding_process, port)"
+    "terminate_process(embedding_process)"
    ]
   }
  ],

docs/backend/openai_api_vision.ipynb

@@ -243,7 +243,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(embedding_process, port)"
+    "terminate_process(embedding_process)"
    ]
   },
   {

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

docs/backend/send_request.ipynb

@@ -243,15 +243,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(server_process, port)"
+    "terminate_process(server_process)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/backend/structured_outputs.ipynb

@@ -397,7 +397,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "terminate_process(server_process, port)"
+    "terminate_process(server_process)"
    ]
   },
   {