SGLang Structured Serving

# pip install (recommended)
pip install "sglang[all]"

# With FlashInfer (faster, CUDA 11.8/12.1)
pip install sglang[all] flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/

# From source
git clone https://github.com/sgl-project/sglang.git
cd sglang
pip install -e "python[all]"

# Basic server (Llama 3-8B)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
    --port 30000

# With RadixAttention (automatic prefix caching)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-8B-Instruct \
    --port 30000 \
    --enable-radix-cache  # Default: enabled

# Multi-GPU (tensor parallelism)
python -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3-70B-Instruct \
    --tp 4 \
    --port 30000

import sglang as sgl

# Set backend
sgl.set_default_backend(sgl.OpenAI("http://localhost:30000/v1"))

# Simple generation
@sgl.function
def simple_gen(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", max_tokens=100)

# Run
state = simple_gen.run(question="What is the capital of France?")
print(state["answer"])
# Output: "The capital of France is Paris."

import sglang as sgl

@sgl.function
def extract_person(s, text):
    s += f"Extract person information from: {text}\n"
    s += "Output JSON:\n"

    # Constrained JSON generation
    s += sgl.gen(
        "json_output",
        max_tokens=200,
        regex=r'\{"name": "[^"]+", "age": \d+, "occupation": "[^"]+"\}'
    )

# Run
state = extract_person.run(
    text="John Smith is a 35-year-old software engineer."
)
print(state["json_output"])
# Output: {"name": "John Smith", "age": 35, "occupation": "software engineer"}

Request 1: [SYSTEM_PROMPT] + "What's the weather?"
→ Computes full prompt (1000 tokens)

Request 2: [SAME_SYSTEM_PROMPT] + "Book a flight"
→ Reuses system prompt KV cache (998 tokens)
→ Only computes 2 new tokens
→ 5× faster!

@sgl.function
def structured_extraction(s, article):
    s += f"Article: {article}\n\n"
    s += "Extract key information as JSON:\n"

    # JSON schema constraint
    schema = {
        "type": "object",
        "properties": {
            "title": {"type": "string"},
            "author": {"type": "string"},
            "summary": {"type": "string"},
            "sentiment": {"type": "string", "enum": ["positive", "negative", "neutral"]}
        },
        "required": ["title", "author", "summary", "sentiment"]
    }

    s += sgl.gen("info", max_tokens=300, json_schema=schema)

state = structured_extraction.run(article="...")
print(state["info"])
# Output: Valid JSON matching schema

@sgl.function
def extract_email(s, text):
    s += f"Extract email from: {text}\n"
    s += "Email: "

    # Email regex pattern
    s += sgl.gen(
        "email",
        max_tokens=50,
        regex=r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
    )

state = extract_email.run(text="Contact john.doe@example.com for details")
print(state["email"])
# Output: "john.doe@example.com"

@sgl.function
def generate_code(s, description):
    s += f"Generate Python code for: {description}\n"
    s += "```python\n"

    # EBNF grammar for Python
    python_grammar = """
    ?start: function_def
    function_def: "def" NAME "(" [parameters] "):" suite
    parameters: parameter ("," parameter)*
    parameter: NAME
    suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT
    """

    s += sgl.gen("code", max_tokens=200, grammar=python_grammar)
    s += "\n```"

import sglang as sgl

# Define tools
tools = [
    {
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            }
        }
    },
    {
        "name": "book_flight",
        "description": "Book a flight",
        "parameters": {
            "type": "object",
            "properties": {
                "from": {"type": "string"},
                "to": {"type": "string"},
                "date": {"type": "string"}
            }
        }
    }
]

@sgl.function
def agent_workflow(s, user_query, tools):
    # System prompt (cached with RadixAttention)
    s += "You are a helpful assistant with access to tools.\n"
    s += f"Available tools: {tools}\n\n"

    # User query
    s += f"User: {user_query}\n"
    s += "Assistant: "

    # Generate with function calling
    s += sgl.gen(
        "response",
        max_tokens=200,
        tools=tools,  # SGLang handles tool call format
        stop=["User:", "\n\n"]
    )

# Multiple queries reuse system prompt
state1 = agent_workflow.run(
    user_query="What's the weather in NYC?",
    tools=tools
)
# First call: Computes full system prompt

state2 = agent_workflow.run(
    user_query="Book a flight to LA",
    tools=tools
)
# Second call: Reuses system prompt (5× faster)