diff --git a/docs/backend/constrained_decoding.ipynb b/docs/backend/constrained_decoding.ipynb
new file mode 100644
index 000000000..a0ea915f3
--- /dev/null
+++ b/docs/backend/constrained_decoding.ipynb
@@ -0,0 +1,525 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Constrained Decoding Tutorial\n",
+    "\n",
+    "This tutorial shows how to format model outputs using constrained decoding in SGLang."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Constrained Decoding\n",
+    "\n",
+    "With SGLang, You can define a JSON schema, EBNF or regular expression to constrain the model's output.\n",
+    "\n",
+    "[JSON Schema](https://json-schema.org/): Formats output into structured JSON objects with validation rules.\n",
+    "\n",
+    "[EBNF (Extended Backus-Naur Form)](https://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_form): Defines complex syntax rules, especially for recursive patterns like nested structures.\n",
+    "\n",
+    "[Regular Expressions](https://en.wikipedia.org/wiki/Regular_expression): Matches text patterns for simple validation and formatting.\n",
+    "\n",
+    "### Constrained Decoding Backends\n",
+    "\n",
+    "SGLang has two backends: [Outlines](https://github.com/dottxt-ai/outlines) (default) and [XGrammar](https://blog.mlc.ai/2024/11/22/achieving-efficient-flexible-portable-structured-generation-with-xgrammar). We suggest using XGrammar whenever possible for its better performance. For more details, see [XGrammar technical overview](https://blog.mlc.ai/2024/11/22/achieving-efficient-flexible-portable-structured-generation-with-xgrammar).\n",
+    "\n",
+    "* Xgrammar Backend: JSON and EBNF\n",
+    "* Outlines Backend: JSON and regular expressions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## OpenAI Compatible API"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To use Xgrammar, simply add `--grammar-backend xgrammar` when launching the server. If no backend is specified, Outlines will be used as the default."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sglang.utils import (\n",
+    "    execute_shell_command,\n",
+    "    wait_for_server,\n",
+    "    terminate_process,\n",
+    "    print_highlight,\n",
+    ")\n",
+    "import openai\n",
+    "\n",
+    "server_process = execute_shell_command(\n",
+    "    \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0 --grammar-backend xgrammar\"\n",
+    ")\n",
+    "\n",
+    "wait_for_server(\"http://localhost:30000\")\n",
+    "client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "json_schema = json.dumps(\n",
+    "    {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"name\": {\"type\": \"string\", \"pattern\": \"^[\\\\w]+$\"},\n",
+    "            \"population\": {\"type\": \"integer\"},\n",
+    "        },\n",
+    "        \"required\": [\"name\", \"population\"],\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "response = client.chat.completions.create(\n",
+    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
+    "    messages=[\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": \"Give me the information of the capital of France in the JSON format.\",\n",
+    "        },\n",
+    "    ],\n",
+    "    temperature=0,\n",
+    "    max_tokens=128,\n",
+    "    response_format={\n",
+    "        \"type\": \"json_schema\",\n",
+    "        \"json_schema\": {\"name\": \"foo\", \"schema\": json.loads(json_schema)},\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "print_highlight(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### EBNF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ebnf_grammar = \"\"\"\n",
+    "root ::= city | description\n",
+    "city ::= \"London\" | \"Paris\" | \"Berlin\" | \"Rome\"\n",
+    "description ::= city \" is \" status\n",
+    "status ::= \"the capital of \" country\n",
+    "country ::= \"England\" | \"France\" | \"Germany\" | \"Italy\"\n",
+    "\"\"\"\n",
+    "\n",
+    "response = client.chat.completions.create(\n",
+    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"system\", \"content\": \"You are a helpful geography bot.\"},\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": \"Give me the information of the capital of France.\",\n",
+    "        },\n",
+    "    ],\n",
+    "    temperature=0,\n",
+    "    max_tokens=32,\n",
+    "    extra_body={\"ebnf\": ebnf_grammar},\n",
+    ")\n",
+    "\n",
+    "print_highlight(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terminate_process(server_process)\n",
+    "server_process = execute_shell_command(\n",
+    "    \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0\"\n",
+    ")\n",
+    "\n",
+    "wait_for_server(\"http://localhost:30000\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Regular expression"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = client.chat.completions.create(\n",
+    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"user\", \"content\": \"What is the capital of France?\"},\n",
+    "    ],\n",
+    "    temperature=0,\n",
+    "    max_tokens=128,\n",
+    "    extra_body={\"regex\": \"(Paris|London)\"},\n",
+    ")\n",
+    "\n",
+    "print_highlight(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terminate_process(server_process)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Native API and SGLang Runtime (SRT)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sglang.utils import (\n",
+    "    execute_shell_command,\n",
+    "    wait_for_server,\n",
+    "    terminate_process,\n",
+    "    print_highlight,\n",
+    ")\n",
+    "\n",
+    "import requests\n",
+    "\n",
+    "server_process = execute_shell_command(\n",
+    "    \"\"\"\n",
+    "python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --port=30010 --grammar-backend xgrammar\n",
+    "\"\"\"\n",
+    ")\n",
+    "\n",
+    "wait_for_server(\"http://localhost:30010\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import requests\n",
+    "\n",
+    "json_schema = json.dumps(\n",
+    "    {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"name\": {\"type\": \"string\", \"pattern\": \"^[\\\\w]+$\"},\n",
+    "            \"population\": {\"type\": \"integer\"},\n",
+    "        },\n",
+    "        \"required\": [\"name\", \"population\"],\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "# JSON\n",
+    "response = requests.post(\n",
+    "    \"http://localhost:30010/generate\",\n",
+    "    json={\n",
+    "        \"text\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
+    "        \"sampling_params\": {\n",
+    "            \"temperature\": 0,\n",
+    "            \"max_new_tokens\": 64,\n",
+    "            \"json_schema\": json_schema,\n",
+    "        },\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "print_highlight(response.json())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### EBNF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "response = requests.post(\n",
+    "    \"http://localhost:30010/generate\",\n",
+    "    json={\n",
+    "        \"text\": \"Give me the information of the capital of France.\",\n",
+    "        \"sampling_params\": {\n",
+    "            \"max_new_tokens\": 128,\n",
+    "            \"temperature\": 0,\n",
+    "            \"n\": 3,\n",
+    "            \"ebnf\": (\n",
+    "                \"root ::= city | description\\n\"\n",
+    "                'city ::= \"London\" | \"Paris\" | \"Berlin\" | \"Rome\"\\n'\n",
+    "                'description ::= city \" is \" status\\n'\n",
+    "                'status ::= \"the capital of \" country\\n'\n",
+    "                'country ::= \"England\" | \"France\" | \"Germany\" | \"Italy\"'\n",
+    "            ),\n",
+    "        },\n",
+    "        \"stream\": False,\n",
+    "        \"return_logprob\": False,\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "print_highlight(response.json())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terminate_process(server_process)\n",
+    "server_process = execute_shell_command(\n",
+    "    \"\"\"\n",
+    "python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --port=30010\n",
+    "\"\"\"\n",
+    ")\n",
+    "\n",
+    "wait_for_server(\"http://localhost:30010\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Regular expression"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = requests.post(\n",
+    "    \"http://localhost:30010/generate\",\n",
+    "    json={\n",
+    "        \"text\": \"Paris is the capital of\",\n",
+    "        \"sampling_params\": {\n",
+    "            \"temperature\": 0,\n",
+    "            \"max_new_tokens\": 64,\n",
+    "            \"regex\": \"(France|England)\",\n",
+    "        },\n",
+    "    },\n",
+    ")\n",
+    "print_highlight(response.json())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terminate_process(server_process)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Offline Engine API"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sglang as sgl\n",
+    "\n",
+    "llm_xgrammar = sgl.Engine(\n",
+    "    model_path=\"meta-llama/Meta-Llama-3.1-8B-Instruct\", grammar_backend=\"xgrammar\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "prompts = [\n",
+    "    \"Give me the information of the capital of China in the JSON format.\",\n",
+    "    \"Give me the information of the capital of France in the JSON format.\",\n",
+    "    \"Give me the information of the capital of Ireland in the JSON format.\",\n",
+    "]\n",
+    "\n",
+    "json_schema = json.dumps(\n",
+    "    {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"name\": {\"type\": \"string\", \"pattern\": \"^[\\\\w]+$\"},\n",
+    "            \"population\": {\"type\": \"integer\"},\n",
+    "        },\n",
+    "        \"required\": [\"name\", \"population\"],\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "sampling_params = {\"temperature\": 0.1, \"top_p\": 0.95, \"json_schema\": json_schema}\n",
+    "\n",
+    "outputs = llm_xgrammar.generate(prompts, sampling_params)\n",
+    "for prompt, output in zip(prompts, outputs):\n",
+    "    print_highlight(\"===============================\")\n",
+    "    print_highlight(f\"Prompt: {prompt}\\nGenerated text: {output['text']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### EBNF\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompts = [\n",
+    "    \"Give me the information of the capital of France.\",\n",
+    "    \"Give me the information of the capital of Germany.\",\n",
+    "    \"Give me the information of the capital of Italy.\",\n",
+    "]\n",
+    "\n",
+    "sampling_params = {\n",
+    "    \"temperature\": 0.8,\n",
+    "    \"top_p\": 0.95,\n",
+    "    \"ebnf\": (\n",
+    "        \"root ::= city | description\\n\"\n",
+    "        'city ::= \"London\" | \"Paris\" | \"Berlin\" | \"Rome\"\\n'\n",
+    "        'description ::= city \" is \" status\\n'\n",
+    "        'status ::= \"the capital of \" country\\n'\n",
+    "        'country ::= \"England\" | \"France\" | \"Germany\" | \"Italy\"'\n",
+    "    ),\n",
+    "}\n",
+    "\n",
+    "outputs = llm_xgrammar.generate(prompts, sampling_params)\n",
+    "for prompt, output in zip(prompts, outputs):\n",
+    "    print_highlight(\"===============================\")\n",
+    "    print_highlight(f\"Prompt: {prompt}\\nGenerated text: {output['text']}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_xgrammar.shutdown()\n",
+    "llm_outlines = sgl.Engine(model_path=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Regular expression"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompts = [\n",
+    "    \"Please provide information about London as a major global city:\",\n",
+    "    \"Please provide information about Paris as a major global city:\",\n",
+    "]\n",
+    "\n",
+    "sampling_params = {\"temperature\": 0.8, \"top_p\": 0.95, \"regex\": \"(France|England)\"}\n",
+    "\n",
+    "outputs = llm_outlines.generate(prompts, sampling_params)\n",
+    "for prompt, output in zip(prompts, outputs):\n",
+    "    print_highlight(\"===============================\")\n",
+    "    print_highlight(f\"Prompt: {prompt}\\nGenerated text: {output['text']}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_outlines.shutdown()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/docs/index.rst b/docs/index.rst
index 8c6c018c4..d3ec65229 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -29,6 +29,7 @@ The core features include:
    backend/native_api.ipynb
    backend/offline_engine_api.ipynb
    backend/backend.md
+   backend/constrained_decoding.ipynb
 
 
 .. toctree::