Home

Awesome

<div align="center"> <img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400"></img>

PyPI PyPI - Downloads license issue resolution open issues

</div>

| Blog | Paper | Slack |

SGLang is a fast serving framework for large language models and vision language models. It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language. The core features include:

News

<details> <summary>More</summary> </details>

Contents

Install

You can install SGLang using any of the methods below.

Method 1: With pip

pip install --upgrade pip
pip install "sglang[all]"

# Install FlashInfer CUDA kernels
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/

Method 2: From source

# Use the last release branch
git clone -b v0.3.0 https://github.com/sgl-project/sglang.git
cd sglang

pip install --upgrade pip
pip install -e "python[all]"

# Install FlashInfer CUDA kernels
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/

Method 3: Using docker

The docker images are available on Docker Hub as lmsysorg/sglang, built from Dockerfile. Replace <secret> below with your huggingface hub token.

docker run --gpus all \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000

Method 4: Using docker compose

<details> <summary>More</summary>

This method is recommended if you plan to serve it as a service. A better approach is to use the k8s-sglang-service.yaml.

  1. Copy the compose.yml to your local machine
  2. Execute the command docker compose up -d in your terminal.
</details>

Method 5: Run on Kubernetes or Clouds with SkyPilot

<details> <summary>More</summary>

To deploy on Kubernetes or 12+ clouds, you can use SkyPilot.

  1. Install SkyPilot and set up Kubernetes cluster or cloud access: see SkyPilot's documentation.
  2. Deploy on your own infra with a single command and get the HTTP API endpoint:
<details> <summary>SkyPilot YAML: <code>sglang.yaml</code></summary> 
# sglang.yaml
envs:
  HF_TOKEN: null

resources:
  image_id: docker:lmsysorg/sglang:latest
  accelerators: A100
  ports: 30000

run: |
  conda deactivate
  python3 -m sglang.launch_server \
    --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \
    --host 0.0.0.0 \
    --port 30000
</details> 
# Deploy on any cloud or Kubernetes cluster. Use --cloud <cloud> to select a specific cloud provider.
HF_TOKEN=<secret> sky launch -c sglang --env HF_TOKEN sglang.yaml

# Get the HTTP API endpoint
sky status --endpoint 30000 sglang
  1. To further scale up your deployment with autoscaling and failure recovery, check out the SkyServe + SGLang guide.
</details>

Common Notes

Backend: SGLang Runtime (SRT)

The SGLang Runtime (SRT) is an efficient serving engine.

Quick Start

Launch a server

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000

Send a request

curl http://localhost:30000/generate \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Once upon a time,",
    "sampling_params": {
      "max_new_tokens": 16,
      "temperature": 0
    }
  }'

Learn more about the argument format here.

OpenAI Compatible API

In addition, the server supports OpenAI-compatible APIs.

import openai
client = openai.Client(
    base_url="http://127.0.0.1:30000/v1", api_key="EMPTY")

# Text completion
response = client.completions.create(
	model="default",
	prompt="The capital of France is",
	temperature=0,
	max_tokens=32,
)
print(response)

# Chat completion
response = client.chat.completions.create(
    model="default",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant"},
        {"role": "user", "content": "List 3 countries and their capitals."},
    ],
    temperature=0,
    max_tokens=64,
)
print(response)

# Text embedding
response = client.embeddings.create(
    model="default",
    input="How are you today",
)
print(response)

It supports streaming, vision, and most features of the Chat/Completions/Models/Batch endpoints specified by the OpenAI API Reference.

Additional Server Arguments

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --tp 2

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --dp 2 --tp 2

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --mem-fraction-static 0.7

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --chunked-prefill-size 4096

# Node 0
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 0

# Node 1
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 1

Supported Models

Generative Models

Instructions for supporting a new model are here.

Use Models From ModelScope

<details> <summary>More</summary>

To use a model from ModelScope, set the environment variable SGLANG_USE_MODELSCOPE.

export SGLANG_USE_MODELSCOPE=true

Launch Qwen2-7B-Instruct Server

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model-path qwen/Qwen2-7B-Instruct --port 30000
</details>

Run Llama 3.1 405B

<details> <summary>More</summary> 
# Run 405B (fp8) on a single node
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct-FP8 --tp 8

# Run 405B (fp16) on two nodes
## on the first node, replace the `172.16.4.52:20000` with your own first node ip address and port
GLOO_SOCKET_IFNAME=eth0 python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --nccl-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 0 --disable-cuda-graph

## on the first node, replace the `172.16.4.52:20000` with your own first node ip address and port
GLOO_SOCKET_IFNAME=eth0 python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --nccl-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 1 --disable-cuda-graph
</details>

Benchmark Performance

Frontend: Structured Generation Language (SGLang)

The frontend language can be used with local models or API models. It is an alternative to the OpenAI API. You may found it easier to use for complex prompting workflow.

Quick Start

The example below shows how to use sglang to answer a mulit-turn question.

Using Local Models

First, launch a server with

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000

Then, connect to the server and answer a multi-turn question.

from sglang import function, system, user, assistant, gen, set_default_backend, RuntimeEndpoint

@function
def multi_turn_question(s, question_1, question_2):
    s += system("You are a helpful assistant.")
    s += user(question_1)
    s += assistant(gen("answer_1", max_tokens=256))
    s += user(question_2)
    s += assistant(gen("answer_2", max_tokens=256))

set_default_backend(RuntimeEndpoint("http://localhost:30000"))

state = multi_turn_question.run(
    question_1="What is the capital of the United States?",
    question_2="List two local attractions.",
)

for m in state.messages():
    print(m["role"], ":", m["content"])

print(state["answer_1"])

Using OpenAI Models

Set the OpenAI API Key

export OPENAI_API_KEY=sk-******

Then, answer a multi-turn question.

from sglang import function, system, user, assistant, gen, set_default_backend, OpenAI

@function
def multi_turn_question(s, question_1, question_2):
    s += system("You are a helpful assistant.")
    s += user(question_1)
    s += assistant(gen("answer_1", max_tokens=256))
    s += user(question_2)
    s += assistant(gen("answer_2", max_tokens=256))

set_default_backend(OpenAI("gpt-3.5-turbo"))

state = multi_turn_question.run(
    question_1="What is the capital of the United States?",
    question_2="List two local attractions.",
)

for m in state.messages():
    print(m["role"], ":", m["content"])

print(state["answer_1"])

More Examples

Anthropic and VertexAI (Gemini) models are also supported. You can find more examples at examples/quick_start.

Language Feature

To begin with, import sglang.

import sglang as sgl

sglang provides some simple primitives such as gen, select, fork, image. You can implement your prompt flow in a function decorated by sgl.function. You can then invoke the function with run or run_batch. The system will manage the state, chat template, parallelism and batching for you.

The complete code for the examples below can be found at readme_examples.py

Control Flow

You can use any Python code within the function body, including control flow, nested function calls, and external libraries.

@sgl.function
def tool_use(s, question):
    s += "To answer this question: " + question + ". "
    s += "I need to use a " + sgl.gen("tool", choices=["calculator", "search engine"]) + ". "

    if s["tool"] == "calculator":
        s += "The math expression is" + sgl.gen("expression")
    elif s["tool"] == "search engine":
        s += "The key word to search is" + sgl.gen("word")

Parallelism

Use fork to launch parallel prompts. Because sgl.gen is non-blocking, the for loop below issues two generation calls in parallel.

@sgl.function
def tip_suggestion(s):
    s += (
        "Here are two tips for staying healthy: "
        "1. Balanced Diet. 2. Regular Exercise.\n\n"
    )

    forks = s.fork(2)
    for i, f in enumerate(forks):
        f += f"Now, expand tip {i+1} into a paragraph:\n"
        f += sgl.gen(f"detailed_tip", max_tokens=256, stop="\n\n")

    s += "Tip 1:" + forks[0]["detailed_tip"] + "\n"
    s += "Tip 2:" + forks[1]["detailed_tip"] + "\n"
    s += "In summary" + sgl.gen("summary")

Multi-Modality

Use sgl.image to pass an image as input.

@sgl.function
def image_qa(s, image_file, question):
    s += sgl.user(sgl.image(image_file) + question)
    s += sgl.assistant(sgl.gen("answer", max_tokens=256)

See also srt_example_llava.py.

Constrained Decoding

Use regex to specify a regular expression as a decoding constraint. This is only supported for local models.

@sgl.function
def regular_expression_gen(s):
    s += "Q: What is the IP address of the Google DNS servers?\n"
    s += "A: " + sgl.gen(
        "answer",
        temperature=0,
        regex=r"((25[0-5]|2[0-4]\d|[01]?\d\d?).){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)",
    )

JSON Decoding

Use regex to specify a JSON schema with a regular expression.

character_regex = (
    r"""\{\n"""
    + r"""    "name": "[\w\d\s]{1,16}",\n"""
    + r"""    "house": "(Gryffindor|Slytherin|Ravenclaw|Hufflepuff)",\n"""
    + r"""    "blood status": "(Pure-blood|Half-blood|Muggle-born)",\n"""
    + r"""    "occupation": "(student|teacher|auror|ministry of magic|death eater|order of the phoenix)",\n"""
    + r"""    "wand": \{\n"""
    + r"""        "wood": "[\w\d\s]{1,16}",\n"""
    + r"""        "core": "[\w\d\s]{1,16}",\n"""
    + r"""        "length": [0-9]{1,2}\.[0-9]{0,2}\n"""
    + r"""    \},\n"""
    + r"""    "alive": "(Alive|Deceased)",\n"""
    + r"""    "patronus": "[\w\d\s]{1,16}",\n"""
    + r"""    "bogart": "[\w\d\s]{1,16}"\n"""
    + r"""\}"""
)

@sgl.function
def character_gen(s, name):
    s += name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
    s += sgl.gen("json_output", max_tokens=256, regex=character_regex)

See also json_decode.py for an additional example of specifying formats with Pydantic models.

Batching

Use run_batch to run a batch of requests with continuous batching.

@sgl.function
def text_qa(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", stop="\n")

states = text_qa.run_batch(
    [
        {"question": "What is the capital of the United Kingdom?"},
        {"question": "What is the capital of France?"},
        {"question": "What is the capital of Japan?"},
    ],
    progress_bar=True
)

Streaming

Add stream=True to enable streaming.

@sgl.function
def text_qa(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", stop="\n")

state = text_qa.run(
    question="What is the capital of France?",
    temperature=0.1,
    stream=True
)

for out in state.text_iter():
    print(out, end="", flush=True)

Roles

Use sgl.system， sgl.user and sgl.assistant to set roles when using Chat models. You can also define more complex role prompts using begin and end tokens.

@sgl.function
def chat_example(s):
    s += sgl.system("You are a helpful assistant.")
    # Same as: s += s.system("You are a helpful assistant.")

    with s.user():
        s += "Question: What is the capital of France?"

    s += sgl.assistant_begin()
    s += "Answer: " + sgl.gen(max_tokens=100, stop="\n")
    s += sgl.assistant_end()

Tips and Implementation Details

Benchmark And Performance

8b_throughput 70b_fp8_throughput

Learn more at this blog.

Roadmap

Development Roadmap (2024 Q3)

Citation And Acknowledgment

Please cite our paper, SGLang: Efficient Execution of Structured Language Model Programs, if you find the project useful. We also learned from the design and reused code from the following projects: Guidance, vLLM, LightLLM, FlashInfer, Outlines, and LMQL.