docs: Add offline engine launch example and documentation (#3771)

docs/backend/offline_engine_api.ipynb

@@ -18,6 +18,8 @@
     "- Non-streaming asynchronous generation\n",
     "- Streaming asynchronous generation\n",
     "\n",
+    "****To launch the offline engine, `__main__` condition is necessary in your own script because we use \"spawn\" to create subprocesses, for more details please refer to [launch_engine](https://github.com/sgl-project/sglang/blob/main/examples/runtime/engine/launch_engine.py).****\n",
+    "\n",
     "Additionally, you can easily build a custom server on top of the SGLang offline engine. A detailed example working in a python script can be found in [custom_server](https://github.com/sgl-project/sglang/blob/main/examples/runtime/engine/custom_server.py)."
    ]
   },
@@ -45,7 +47,6 @@
     "if is_in_ci():\n",
     "    import patch\n",
     "\n",
-    "\n",
     "llm = sgl.Engine(model_path=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")"
    ]
   },

examples/runtime/engine/launch_engine.py

+"""
+This example demonstrates how to launch the offline engine.
+"""
+
+import sglang as sgl
+
+
+def main():
+    llm = sgl.Engine(model_path="meta-llama/Meta-Llama-3.1-8B-Instruct")
+    llm.generate("What is the capital of France?")
+    llm.shutdown()
+
+
+# The __main__ condition is necessary here because we use "spawn" to create subprocesses
+# Spawn starts a fresh program every time, if there is no __main__, it will run into infinite loop to keep spawning processes from sgl.Engine
+if __name__ == "__main__":
+    main()