README.md 24.3 KB
Newer Older
1
<div align="center"  id="sglangtop">
Kushal Agrawal's avatar
Kushal Agrawal committed
2
<img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" margin="10px"></img>
Lianmin Zheng's avatar
Lianmin Zheng committed
3

Yineng Zhang's avatar
Yineng Zhang committed
4
5
6
7
8
9
[![PyPI](https://img.shields.io/pypi/v/sglang)](https://pypi.org/project/sglang)
![PyPI - Downloads](https://img.shields.io/pypi/dm/sglang)
[![license](https://img.shields.io/github/license/sgl-project/sglang.svg)](https://github.com/sgl-project/sglang/tree/main/LICENSE)
[![issue resolution](https://img.shields.io/github/issues-closed-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
[![open issues](https://img.shields.io/github/issues-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)

Yineng Zhang's avatar
Yineng Zhang committed
10
11
</div>

Lianmin Zheng's avatar
Lianmin Zheng committed
12
13
--------------------------------------------------------------------------------

Lianmin Zheng's avatar
Lianmin Zheng committed
14
| [**Blog**](https://lmsys.org/blog/2024-07-25-sglang-llama3/) | [**Paper**](https://arxiv.org/abs/2312.07104) | [**Slides**](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_dev_day_v2.pdf) | [**Learn More**](https://github.com/sgl-project/sgl-learning-materials) | [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2ngly9muu-t37XiH87qvD~6rVBTkTEHw) |
Lianmin Zheng's avatar
Lianmin Zheng committed
15
[**Join Bi-Weekly Development Meeting (Oct. 19)**](https://calendar.app.google/GYW7S8QGoanCuaxW6) |
Lianmin Zheng's avatar
Lianmin Zheng committed
16

Lianmin Zheng's avatar
Lianmin Zheng committed
17
## News
Lianmin Zheng's avatar
Lianmin Zheng committed
18
19
20
- [2024/10] 🔥 The First SGLang Online Meetup ([slides](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#the-first-sglang-online-meetup)).
- [2024/09] SGLang v0.3 Release: 7x Faster DeepSeek MLA, 1.5x Faster torch.compile, Multi-Image/Video LLaVA-OneVision ([blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)).
- [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
Ying Sheng's avatar
Ying Sheng committed
21

Ying Sheng's avatar
Ying Sheng committed
22
23
24
<details>
<summary>More</summary>

25
- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
26
- [2024/04] SGLang is used by the official **LLaVA-NeXT (video)** release ([blog](https://llava-vl.github.io/blog/2024-04-30-llava-next-video/)).
Ying Sheng's avatar
Ying Sheng committed
27
- [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
Ying Sheng's avatar
Ying Sheng committed
28
29
30
31
- [2024/01] SGLang powers the serving of the official **LLaVA v1.6** release demo ([usage](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#demo)).

</details>

Ying Sheng's avatar
Ying Sheng committed
32
33
34
35
36
37
38
## About
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:

- **Fast Backend Runtime**: Provides efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, continuous batching, token attention (paged attention), tensor parallelism, FlashInfer kernels, chunked prefill, and quantization (INT4/FP8/AWQ/GPTQ).
- **Flexible Frontend Language**: Offers an intuitive interface for programming LLM applications, including chained generation calls, advanced prompting, control flow, multi-modal inputs, parallelism, and external interactions.
Lianmin Zheng's avatar
Lianmin Zheng committed
39
- **Extensive Model Support**: Supports a wide range of generative models (Llama, Gemma, Mistral, QWen, DeepSeek, LLaVA, etc.) and embedding models (e5-mistral), with easy extensibility for integrating new models.
Ying Sheng's avatar
Ying Sheng committed
40
41
- **Active Community**: SGLang is open-source and backed by an active community with industry adoption.

Lianmin Zheng's avatar
Lianmin Zheng committed
42
43
44
## Contents
- [Install](#install)
- [Backend: SGLang Runtime (SRT)](#backend-sglang-runtime-srt)
Ying Sheng's avatar
Ying Sheng committed
45
- [Frontend: Structured Generation Language (SGLang)](#frontend-structured-generation-language-sglang)
Lianmin Zheng's avatar
Lianmin Zheng committed
46
47
48
49
50
51
- [Benchmark And Performance](#benchmark-and-performance)
- [Roadmap](#roadmap)
- [Citation And Acknowledgment](#citation-and-acknowledgment)

## Install

52
53
You can install SGLang using any of the methods below.

Lianmin Zheng's avatar
Lianmin Zheng committed
54
55
### Method 1: With pip
```
56
pip install --upgrade pip
Lianmin Zheng's avatar
Lianmin Zheng committed
57
pip install "sglang[all]"
Lianmin Zheng's avatar
Lianmin Zheng committed
58

Lianmin Zheng's avatar
Lianmin Zheng committed
59
# Install FlashInfer CUDA kernels
60
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
Lianmin Zheng's avatar
Lianmin Zheng committed
61
```
62

Lianmin Zheng's avatar
Lianmin Zheng committed
63
### Method 2: From source
Lianmin Zheng's avatar
Lianmin Zheng committed
64
```
Ying Sheng's avatar
Ying Sheng committed
65
# Use the last release branch
Lianmin Zheng's avatar
Lianmin Zheng committed
66
git clone -b v0.3.4 https://github.com/sgl-project/sglang.git
Lianmin Zheng's avatar
Lianmin Zheng committed
67
68
cd sglang

Lianmin Zheng's avatar
Lianmin Zheng committed
69
pip install --upgrade pip
Lianmin Zheng's avatar
Lianmin Zheng committed
70
71
pip install -e "python[all]"

Lianmin Zheng's avatar
Lianmin Zheng committed
72
# Install FlashInfer CUDA kernels
73
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
Lianmin Zheng's avatar
Lianmin Zheng committed
74
```
75

Lianmin Zheng's avatar
Lianmin Zheng committed
76
### Method 3: Using docker
77
The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags), built from [Dockerfile](https://github.com/sgl-project/sglang/tree/main/docker).
78
Replace `<secret>` below with your huggingface hub [token](https://huggingface.co/docs/hub/en/security-tokens).
Ying Sheng's avatar
Ying Sheng committed
79

Liangsheng Yin's avatar
Liangsheng Yin committed
80
81
82
83
```bash
docker run --gpus all \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
84
    --env "HF_TOKEN=<secret>" \
Liangsheng Yin's avatar
Liangsheng Yin committed
85
86
    --ipc=host \
    lmsysorg/sglang:latest \
87
    python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000
Liangsheng Yin's avatar
Liangsheng Yin committed
88
89
```

90
91
### Method 4: Using docker compose

92
<details>
Dr. Artificial曾小健's avatar
Dr. Artificial曾小健 committed
93
<summary>More</summary>
94

95
> This method is recommended if you plan to serve it as a service.
96
> A better approach is to use the [k8s-sglang-service.yaml](docker/k8s-sglang-service.yaml).
97

98
1. Copy the [compose.yml](docker/compose.yaml) to your local machine
99
2. Execute the command `docker compose up -d` in your terminal.
100
</details>
101

102
103
### Method 5: Run on Kubernetes or Clouds with SkyPilot

104
<details>
Dr. Artificial曾小健's avatar
Dr. Artificial曾小健 committed
105
<summary>More</summary>
106

107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
To deploy on Kubernetes or 12+ clouds, you can use [SkyPilot](https://github.com/skypilot-org/skypilot).

1. Install SkyPilot and set up Kubernetes cluster or cloud access: see [SkyPilot's documentation](https://skypilot.readthedocs.io/en/latest/getting-started/installation.html).
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>

```yaml
# 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 \
127
    --model-path meta-llama/Llama-3.1-8B-Instruct \
128
129
130
    --host 0.0.0.0 \
    --port 30000
```
131
</details>
132
133
134
135
136
137
138
139
140

```bash
# 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
```
3. To further scale up your deployment with autoscaling and failure recovery, check out the [SkyServe + SGLang guide](https://github.com/skypilot-org/skypilot/tree/master/llm/sglang#serving-llama-2-with-sglang-for-more-traffic-using-skyserve).
141
</details>
142
143


Lianmin Zheng's avatar
Lianmin Zheng committed
144
### Common Notes
Lianmin Zheng's avatar
Lianmin Zheng committed
145
- [FlashInfer](https://github.com/flashinfer-ai/flashinfer) is the default attention kernel backend. It only supports sm75 and above. If you encounter any FlashInfer-related issues on sm75+ devices (e.g., T4, A10, A100, L4, L40S, H100), please switch to other kernels by adding `--attention-backend triton --sampling-backend pytorch` and open an issue on GitHub.
Lianmin Zheng's avatar
Lianmin Zheng committed
146
- If you only need to use the OpenAI backend, you can avoid installing other dependencies by using `pip install "sglang[openai]"`.
Ying Sheng's avatar
Ying Sheng committed
147

Ying Sheng's avatar
Ying Sheng committed
148
149
150
## Backend: SGLang Runtime (SRT)
The SGLang Runtime (SRT) is an efficient serving engine.

Ying Sheng's avatar
Ying Sheng committed
151
### Quick Start
Ying Sheng's avatar
Ying Sheng committed
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
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
    }
  }'
```
Lianmin Zheng's avatar
Lianmin Zheng committed
169
170

Learn more about the argument specification, streaming, and multi-modal support [here](docs/en/sampling_params.md).
Ying Sheng's avatar
Ying Sheng committed
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199

### OpenAI Compatible API
In addition, the server supports OpenAI-compatible APIs.

```python
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)
200
201
202
203
204
205
206

# Text embedding
response = client.embeddings.create(
    model="default",
    input="How are you today",
)
print(response)
Ying Sheng's avatar
Ying Sheng committed
207
208
```

Lianmin Zheng's avatar
Lianmin Zheng committed
209
It supports streaming, vision, and almost all features of the Chat/Completions/Models/Batch endpoints specified by the [OpenAI API Reference](https://platform.openai.com/docs/api-reference/).
Ying Sheng's avatar
Ying Sheng committed
210
211

### Additional Server Arguments
212
- To enable multi-GPU tensor parallelism, add `--tp 2`. If it reports the error "peer access is not supported between these two devices", add `--enable-p2p-check` to the server launch command.
Ying Sheng's avatar
Ying Sheng committed
213
```
214
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 2
Ying Sheng's avatar
Ying Sheng committed
215
```
216
- To enable multi-GPU data parallelism, add `--dp 2`. Data parallelism is better for throughput if there is enough memory. It can also be used together with tensor parallelism. The following command uses 4 GPUs in total.
Ying Sheng's avatar
Ying Sheng committed
217
```
218
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --dp 2 --tp 2
Ying Sheng's avatar
Ying Sheng committed
219
```
220
- If you see out-of-memory errors during serving, try to reduce the memory usage of the KV cache pool by setting a smaller value of `--mem-fraction-static`. The default value is `0.9`.
Ying Sheng's avatar
Ying Sheng committed
221
```
222
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --mem-fraction-static 0.7
Ying Sheng's avatar
Ying Sheng committed
223
```
224
225
- See [hyperparameter_tuning.md](docs/en/hyperparameter_tuning.md) on tuning hyperparameters for better performance.
- If you see out-of-memory errors during prefill for long prompts, try to set a smaller chunked prefill size.
Ying Sheng's avatar
Ying Sheng committed
226
```
227
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --chunked-prefill-size 4096
Ying Sheng's avatar
Ying Sheng committed
228
```
229
- To enable torch.compile acceleration, add `--enable-torch-compile`. It accelerates small models on small batch sizes.
Lianmin Zheng's avatar
Lianmin Zheng committed
230
- To enable torchao quantization, add `--torchao-config int4wo-128`. It supports various quantization strategies.
231
232
233
- To enable fp8 weight quantization, add `--quantization fp8` on a fp16 checkpoint or directly load a fp8 checkpoint without specifying any arguments.
- To enable fp8 kv cache quantization, add `--kv-cache-dtype fp8_e5m2`.
- If the model does not have a chat template in the Hugging Face tokenizer, you can specify a [custom chat template](docs/en/custom_chat_template.md).
234
- To run tensor parallelism on multiple nodes, add `--nnodes 2`. If you have two nodes with two GPUs on each node and want to run TP=4, let `sgl-dev-0` be the hostname of the first node and `50000` be an available port, you can use the following commands. If you meet deadlock, please try to add `--disable-cuda-graph`
Ying Sheng's avatar
Ying Sheng committed
235
236
```
# Node 0
237
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
Ying Sheng's avatar
Ying Sheng committed
238
239

# Node 1
240
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
Ying Sheng's avatar
Ying Sheng committed
241
```
Lianmin Zheng's avatar
Lianmin Zheng committed
242
 
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
### Engine Without HTTP Server

We also provide an inference engine **without a HTTP server**. For example,

```python
import sglang as sgl


def main():
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]
    sampling_params = {"temperature": 0.8, "top_p": 0.95}
    llm = sgl.Engine(model_path="meta-llama/Meta-Llama-3.1-8B-Instruct")

    outputs = llm.generate(prompts, sampling_params)
    for prompt, output in zip(prompts, outputs):
        print("===============================")
        print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

if __name__ == "__main__":
    main()
```

This can be used for:

1. **Offline Batch Inference**
2. **Building Custom Servers**

You can view the full example [here](https://github.com/sgl-project/sglang/tree/main/examples/runtime/engine)

Ying Sheng's avatar
Ying Sheng committed
277
278
### Supported Models

279
**Generative Models**
280
- Llama / Llama 2 / Llama 3 / Llama 3.1
281
- Mistral / Mixtral / Mistral NeMo
Ying Sheng's avatar
Ying Sheng committed
282
283
- Gemma / Gemma 2
- Qwen / Qwen 2 / Qwen 2 MoE
284
- DeepSeek / DeepSeek 2
Lianmin Zheng's avatar
Lianmin Zheng committed
285
- OLMoE
286
- [LLaVA-OneVision](https://llava-vl.github.io/blog/2024-08-05-llava-onevision/)
287
  - `python3 -m sglang.launch_server --model-path lmms-lab/llava-onevision-qwen2-7b-ov --port=30000 --chat-template=chatml-llava`
288
  - `python3 -m sglang.launch_server --model-path lmms-lab/llava-onevision-qwen2-72b-ov --port=30000 --tp-size=8 --chat-template=chatml-llava`
289
290
291
292
293
  - Query the server with the [OpenAI Vision API](https://platform.openai.com/docs/guides/vision). See examples at [test/srt/test_vision_openai_server.py](test/srt/test_vision_openai_server.py)
- LLaVA 1.5 / 1.6 / NeXT
  - `python -m sglang.launch_server --model-path lmms-lab/llama3-llava-next-8b --port=30000 --tp-size=1 --chat-template=llava_llama_3`
  - `python -m sglang.launch_server --model-path lmms-lab/llava-next-72b --port=30000 --tp-size=8 --chat-template=chatml-llava`
  - Query the server with the [OpenAI Vision API](https://platform.openai.com/docs/guides/vision). See examples at [test/srt/test_vision_openai_server.py](test/srt/test_vision_openai_server.py)
Ying Sheng's avatar
Ying Sheng committed
294
295
296
297
298
299
300
- Yi-VL
- StableLM
- Command-R
- DBRX
- Grok
- ChatGLM
- InternLM 2
301
- Exaone 3
Vectory's avatar
Vectory committed
302
- BaiChuan2
William's avatar
William committed
303
- MiniCPM / MiniCPM 3
304
- XVERSE / XVERSE MoE
305
- SmolLM
William's avatar
William committed
306

307
308
309
310
311
312
**Embedding Models**

- e5-mistral
- gte-Qwen2
  - `python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct --is-embedding`

313
Instructions for supporting a new model are [here](docs/en/model_support.md).
Ying Sheng's avatar
Ying Sheng committed
314

Lianmin Zheng's avatar
Lianmin Zheng committed
315
#### Use Models From ModelScope
316
<details>
Dr. Artificial曾小健's avatar
Dr. Artificial曾小健 committed
317
<summary>More</summary>
318

Lianmin Zheng's avatar
Lianmin Zheng committed
319
To use a model from [ModelScope](https://www.modelscope.cn), set the environment variable SGLANG_USE_MODELSCOPE.
Lianmin Zheng's avatar
Lianmin Zheng committed
320
321
322
323
324
325
```
export SGLANG_USE_MODELSCOPE=true
```
Launch [Qwen2-7B-Instruct](https://www.modelscope.cn/models/qwen/qwen2-7b-instruct) Server
```
SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model-path qwen/Qwen2-7B-Instruct --port 30000
Lianmin Zheng's avatar
Lianmin Zheng committed
326
```
327
328
329
330
331
332
333
334
335
336
337

Or start it by docker.
```bash
docker run --gpus all \
    -p 30000:30000 \
    -v ~/.cache/modelscope:/root/.cache/modelscope \
    --env "SGLANG_USE_MODELSCOPE=true" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-7B-Instruct --host 0.0.0.0 --port 30000
```
Lianmin Zheng's avatar
Lianmin Zheng committed
338
  
339
</details>
Lianmin Zheng's avatar
Lianmin Zheng committed
340
341

#### Run Llama 3.1 405B
Lianmin Zheng's avatar
Lianmin Zheng committed
342
<details>
Dr. Artificial曾小健's avatar
Dr. Artificial曾小健 committed
343
<summary>More</summary>
Ying Sheng's avatar
Ying Sheng committed
344
345

```bash
346
# Run 405B (fp8) on a single node
Ying Sheng's avatar
Ying Sheng committed
347
348
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct-FP8 --tp 8

349
350
351
# 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
Ying Sheng's avatar
Ying Sheng committed
352

353
354
## 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
Ying Sheng's avatar
Ying Sheng committed
355
356
```

Lianmin Zheng's avatar
Lianmin Zheng committed
357
358
</details>

Ying Sheng's avatar
Ying Sheng committed
359
360
### Benchmark Performance

Lianmin Zheng's avatar
Lianmin Zheng committed
361
362
363
- Benchmark a single static batch by running the following command without launching a server. The arguments are the same as for `launch_server.py`.
  Note that this is not a dynamic batching server, so it may run out of memory for a batch size that a real server can handle.
  A real server truncates the prefill into several batches, while this unit test does not. For accurate large batch testing, please use `sglang.bench_serving` instead.
Ying Sheng's avatar
Ying Sheng committed
364
  ```
365
  python -m sglang.bench_latency --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 32 --input-len 256 --output-len 32
Ying Sheng's avatar
Ying Sheng committed
366
367
368
  ```
- Benchmark online serving. Launch a server first and run the following command.
  ```
369
  python3 -m sglang.bench_serving --backend sglang --num-prompt 10
Ying Sheng's avatar
Ying Sheng committed
370
371
  ```

Ying Sheng's avatar
Ying Sheng committed
372
## Frontend: Structured Generation Language (SGLang)
373
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.
Ying Sheng's avatar
Ying Sheng committed
374
375

### Quick Start
376
The example below shows how to use sglang to answer a multi-turn question.
Lianmin Zheng's avatar
Lianmin Zheng committed
377

Ying Sheng's avatar
Ying Sheng committed
378
#### Using Local Models
379
First, launch a server with
Lianmin Zheng's avatar
Lianmin Zheng committed
380
```
Ying Sheng's avatar
Ying Sheng committed
381
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000
Lianmin Zheng's avatar
Lianmin Zheng committed
382
383
```

384
385
Then, connect to the server and answer a multi-turn question.

Lianmin Zheng's avatar
Lianmin Zheng committed
386
```python
387
from sglang import function, system, user, assistant, gen, set_default_backend, RuntimeEndpoint
Lianmin Zheng's avatar
Lianmin Zheng committed
388
389
390
391
392
393
394
395
396

@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))

397
set_default_backend(RuntimeEndpoint("http://localhost:30000"))
Lianmin Zheng's avatar
Lianmin Zheng committed
398
399
400
401
402
403
404
405

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"])
406
407

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
408
409
```

Ying Sheng's avatar
Ying Sheng committed
410
#### Using OpenAI Models
411
Set the OpenAI API Key
Lianmin Zheng's avatar
Lianmin Zheng committed
412
```
413
export OPENAI_API_KEY=sk-******
Lianmin Zheng's avatar
Lianmin Zheng committed
414
415
```

416
Then, answer a multi-turn question.
Lianmin Zheng's avatar
Lianmin Zheng committed
417
```python
418
from sglang import function, system, user, assistant, gen, set_default_backend, OpenAI
Lianmin Zheng's avatar
Lianmin Zheng committed
419
420
421
422
423
424
425
426
427

@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))

428
set_default_backend(OpenAI("gpt-3.5-turbo"))
Lianmin Zheng's avatar
Lianmin Zheng committed
429
430
431
432
433
434
435
436

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"])
437
438

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
439
440
```

Ying Sheng's avatar
Ying Sheng committed
441
#### More Examples
Lianmin Zheng's avatar
Lianmin Zheng committed
442

443
Anthropic and VertexAI (Gemini) models are also supported.
Byron Hsu's avatar
Byron Hsu committed
444
You can find more examples at [examples/quick_start](examples/frontend_language/quick_start).
Lianmin Zheng's avatar
Lianmin Zheng committed
445

Ying Sheng's avatar
Ying Sheng committed
446
### Language Feature
Lianmin Zheng's avatar
Lianmin Zheng committed
447
448
449
450
451
To begin with, import sglang.
```python
import sglang as sgl
```

Lianmin Zheng's avatar
Lianmin Zheng committed
452
`sglang` provides some simple primitives such as `gen`, `select`, `fork`, `image`.
Lianmin Zheng's avatar
Lianmin Zheng committed
453
454
You can implement your prompt flow in a function decorated by `sgl.function`.
You can then invoke the function with `run` or `run_batch`.
455
The system will manage the state, chat template, parallelism and batching for you.
Lianmin Zheng's avatar
Lianmin Zheng committed
456

457
The complete code for the examples below can be found at [readme_examples.py](examples/frontend_language/usage/readme_examples.py)
458

Ying Sheng's avatar
Ying Sheng committed
459
#### Control Flow
Lianmin Zheng's avatar
Lianmin Zheng committed
460
461
You can use any Python code within the function body, including control flow, nested function calls, and external libraries.

Lianmin Zheng's avatar
Lianmin Zheng committed
462
463
```python
@sgl.function
464
465
466
def tool_use(s, question):
    s += "To answer this question: " + question + ". "
    s += "I need to use a " + sgl.gen("tool", choices=["calculator", "search engine"]) + ". "
Lianmin Zheng's avatar
Lianmin Zheng committed
467
468
469

    if s["tool"] == "calculator":
        s += "The math expression is" + sgl.gen("expression")
470
471
    elif s["tool"] == "search engine":
        s += "The key word to search is" + sgl.gen("word")
Lianmin Zheng's avatar
Lianmin Zheng committed
472
```
Lianmin Zheng's avatar
Lianmin Zheng committed
473

Ying Sheng's avatar
Ying Sheng committed
474
#### Parallelism
Lianmin Zheng's avatar
Lianmin Zheng committed
475
476
477
Use `fork` to launch parallel prompts.
Because `sgl.gen` is non-blocking, the for loop below issues two generation calls in parallel.

Lianmin Zheng's avatar
Lianmin Zheng committed
478
479
480
481
482
483
484
485
```python
@sgl.function
def tip_suggestion(s):
    s += (
        "Here are two tips for staying healthy: "
        "1. Balanced Diet. 2. Regular Exercise.\n\n"
    )

Lianmin Zheng's avatar
Lianmin Zheng committed
486
    forks = s.fork(2)
Lianmin Zheng's avatar
Lianmin Zheng committed
487
488
489
490
491
492
493
494
    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")
```
Lianmin Zheng's avatar
Lianmin Zheng committed
495

Lianmin Zheng's avatar
Lianmin Zheng committed
496
#### Multi-Modality
Lianmin Zheng's avatar
Lianmin Zheng committed
497
498
Use `sgl.image` to pass an image as input.

Lianmin Zheng's avatar
Lianmin Zheng committed
499
500
```python
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
501
def image_qa(s, image_file, question):
Lianmin Zheng's avatar
Lianmin Zheng committed
502
    s += sgl.user(sgl.image(image_file) + question)
Lianmin Zheng's avatar
Lianmin Zheng committed
503
    s += sgl.assistant(sgl.gen("answer", max_tokens=256)
Lianmin Zheng's avatar
Lianmin Zheng committed
504
505
```

506
See also [srt_example_llava.py](examples/frontend_language/quick_start/local_example_llava_next.py).
507

Ying Sheng's avatar
Ying Sheng committed
508
#### Constrained Decoding
509
510
Use `regex` to specify a regular expression as a decoding constraint.
This is only supported for local models.
Lianmin Zheng's avatar
Lianmin Zheng committed
511

Lianmin Zheng's avatar
Lianmin Zheng committed
512
```python
Lianmin Zheng's avatar
Lianmin Zheng committed
513
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
514
515
def regular_expression_gen(s):
    s += "Q: What is the IP address of the Google DNS servers?\n"
Lianmin Zheng's avatar
Lianmin Zheng committed
516
    s += "A: " + sgl.gen(
Lianmin Zheng's avatar
Lianmin Zheng committed
517
518
519
520
521
        "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?)",
    )
```
Lianmin Zheng's avatar
Lianmin Zheng committed
522

Ying Sheng's avatar
Ying Sheng committed
523
#### JSON Decoding
Lianmin Zheng's avatar
Lianmin Zheng committed
524
Use `regex` to specify a JSON schema with a regular expression.
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545

```python
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):
Lianmin Zheng's avatar
Lianmin Zheng committed
546
    s += name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
547
548
549
    s += sgl.gen("json_output", max_tokens=256, regex=character_regex)
```

550
See also [json_decode.py](examples/frontend_language/usage/json_decode.py) for an additional example of specifying formats with Pydantic models.
551

Ying Sheng's avatar
Ying Sheng committed
552
#### Batching
Lianmin Zheng's avatar
Lianmin Zheng committed
553
554
Use `run_batch` to run a batch of requests with continuous batching.

Lianmin Zheng's avatar
Lianmin Zheng committed
555
556
557
558
559
560
561
562
563
564
565
566
```python
@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?"},
    ],
Lianmin Zheng's avatar
Lianmin Zheng committed
567
    progress_bar=True
Lianmin Zheng's avatar
Lianmin Zheng committed
568
569
)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
570

Ying Sheng's avatar
Ying Sheng committed
571
#### Streaming
Lianmin Zheng's avatar
Lianmin Zheng committed
572
573
Add `stream=True` to enable streaming.

Lianmin Zheng's avatar
Lianmin Zheng committed
574
575
576
577
578
579
```python
@sgl.function
def text_qa(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", stop="\n")

580
state = text_qa.run(
Lianmin Zheng's avatar
Lianmin Zheng committed
581
    question="What is the capital of France?",
Lianmin Zheng's avatar
Lianmin Zheng committed
582
583
584
    temperature=0.1,
    stream=True
)
Lianmin Zheng's avatar
Lianmin Zheng committed
585

Lianmin Zheng's avatar
Lianmin Zheng committed
586
587
588
for out in state.text_iter():
    print(out, end="", flush=True)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
589

590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
#### 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.

```python
@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()
```

Ying Sheng's avatar
Ying Sheng committed
608
#### Tips and Implementation Details
609
610
- The `choices` argument in `sgl.gen` is implemented by computing the [token-length normalized log probabilities](https://blog.eleuther.ai/multiple-choice-normalization/) of all choices and selecting the one with the highest probability.
- The `regex` argument in `sgl.gen` is implemented through autoregressive decoding with logit bias masking, according to the constraints set by the regex. It is compatible with `temperature=0` and `temperature != 0`.
Lianmin Zheng's avatar
Lianmin Zheng committed
611

Ying Sheng's avatar
Ying Sheng committed
612
## Benchmark And Performance
Lianmin Zheng's avatar
Lianmin Zheng committed
613
Learn more in our release blogs: [v0.2](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3](https://lmsys.org/blog/2024-09-04-sglang-v0-3/).
Lianmin Zheng's avatar
Lianmin Zheng committed
614

Lianmin Zheng's avatar
Lianmin Zheng committed
615
## Roadmap
616
[Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
Lianmin Zheng's avatar
Lianmin Zheng committed
617
618

## Citation And Acknowledgment
Ying Sheng's avatar
Ying Sheng committed
619
620
Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
We also learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
621
622
623
624
625
626
627
628



<p align="center">
  <a href="#sglangtop" target="_blank">
  <bold>Back To Top </bold>
  </a>
</p>