README.md 18.8 KB
Newer Older
Lianmin Zheng's avatar
Lianmin Zheng committed
1
<div align="center">
2
<img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400"></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
--------------------------------------------------------------------------------

Ying Sheng's avatar
Ying Sheng committed
14
| [**Blog**](https://lmsys.org/blog/2024-07-25-sglang-llama3/) | [**Paper**](https://arxiv.org/abs/2312.07104) | [**Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2ngly9muu-t37XiH87qvD~6rVBTkTEHw) |
Lianmin Zheng's avatar
Lianmin Zheng committed
15

Ying Sheng's avatar
Ying Sheng committed
16
17
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.
Lianmin Zheng's avatar
Lianmin Zheng committed
18

19
The core features include:
Ying Sheng's avatar
Ying Sheng committed
20
- **Fast Backend Runtime**: Efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, continuous batching, token attention (paged attention), tensor parallelism, flashinfer kernels, and quantization (AWQ/FP8/GPTQ/Marlin).
Lianmin Zheng's avatar
Lianmin Zheng committed
21
- **Flexible Frontend Language**: Enables easy programming of LLM applications with chained generation calls, advanced prompting, control flow, multiple modalities, parallelism, and external interactions.
Lianmin Zheng's avatar
Lianmin Zheng committed
22

Ying Sheng's avatar
Ying Sheng committed
23
## News
Ying Sheng's avatar
Ying Sheng committed
24
25
26
- [2024/07] 🔥 Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
- [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/)).
- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
Ying Sheng's avatar
Ying Sheng committed
27

Ying Sheng's avatar
Ying Sheng committed
28
29
30
<details>
<summary>More</summary>

Ying Sheng's avatar
Ying Sheng committed
31
- [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
32
33
34
35
- [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>

Lianmin Zheng's avatar
Lianmin Zheng committed
36
37
38
## Contents
- [Install](#install)
- [Backend: SGLang Runtime (SRT)](#backend-sglang-runtime-srt)
Ying Sheng's avatar
Ying Sheng committed
39
- [Frontend: Structured Generation Language (SGLang)](#frontend-structured-generation-language-sglang)
Lianmin Zheng's avatar
Lianmin Zheng committed
40
41
42
43
44
45
- [Benchmark And Performance](#benchmark-and-performance)
- [Roadmap](#roadmap)
- [Citation And Acknowledgment](#citation-and-acknowledgment)

## Install

Lianmin Zheng's avatar
Lianmin Zheng committed
46
47
### Method 1: With pip
```
48
pip install --upgrade pip
Lianmin Zheng's avatar
Lianmin Zheng committed
49
pip install "sglang[all]"
Lianmin Zheng's avatar
Lianmin Zheng committed
50

Lianmin Zheng's avatar
Lianmin Zheng committed
51
# Install FlashInfer CUDA kernels
52
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
Lianmin Zheng's avatar
Lianmin Zheng committed
53
```
54

Lianmin Zheng's avatar
Lianmin Zheng committed
55
### Method 2: From source
Lianmin Zheng's avatar
Lianmin Zheng committed
56
```
Ying Sheng's avatar
Ying Sheng committed
57
# Use the last release branch
Yineng Zhang's avatar
Yineng Zhang committed
58
git clone -b v0.2.11 https://github.com/sgl-project/sglang.git
Lianmin Zheng's avatar
Lianmin Zheng committed
59
60
cd sglang

Lianmin Zheng's avatar
Lianmin Zheng committed
61
pip install --upgrade pip
Lianmin Zheng's avatar
Lianmin Zheng committed
62
63
pip install -e "python[all]"

Lianmin Zheng's avatar
Lianmin Zheng committed
64
# Install FlashInfer CUDA kernels
65
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
Lianmin Zheng's avatar
Lianmin Zheng committed
66
```
67

Lianmin Zheng's avatar
Lianmin Zheng committed
68
### Method 3: Using docker
Ying Sheng's avatar
Ying Sheng committed
69
The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags), built from [Dockerfile](docker).
70
Replace `<secret>` below with your huggingface hub [token](https://huggingface.co/docs/hub/en/security-tokens).
Ying Sheng's avatar
Ying Sheng committed
71

Liangsheng Yin's avatar
Liangsheng Yin committed
72
73
74
75
```bash
docker run --gpus all \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
76
    --env "HF_TOKEN=<secret>" \
Liangsheng Yin's avatar
Liangsheng Yin committed
77
78
    --ipc=host \
    lmsysorg/sglang:latest \
Ying Sheng's avatar
Ying Sheng committed
79
    python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --host 0.0.0.0 --port 30000
Liangsheng Yin's avatar
Liangsheng Yin committed
80
81
```

Lianmin Zheng's avatar
Lianmin Zheng committed
82
### Common Notes
Lianmin Zheng's avatar
Lianmin Zheng committed
83
84
- If you cannot install FlashInfer, check out its [installation](https://docs.flashinfer.ai/installation.html#) page. If you still cannot install it, you can use the slower Triton kernels by adding `--disable-flashinfer` when launching the server.
- 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
85

Ying Sheng's avatar
Ying Sheng committed
86
87
88
## Backend: SGLang Runtime (SRT)
The SGLang Runtime (SRT) is an efficient serving engine.

Ying Sheng's avatar
Ying Sheng committed
89
### Quick Start
Ying Sheng's avatar
Ying Sheng committed
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
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
    }
  }'
```
107
Learn more about the argument format [here](docs/en/sampling_params.md).
Ying Sheng's avatar
Ying Sheng committed
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138

### 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)
```

Ying Sheng's avatar
Ying Sheng committed
139
It supports streaming, vision, and most 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
140
141
142
143
144
145
146
147
148
149

### Additional Server Arguments
- Add `--tp 2` to enable tensor parallelism. If it indicates `peer access is not supported between these two devices`, add `--enable-p2p-check` option.
```
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --tp 2
```
- Add `--dp 2` to enable data parallelism. It can also be used together with tp. Data parallelism is better for throughput if there is enough memory.
```
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --dp 2 --tp 2
```
Ying Sheng's avatar
Ying Sheng committed
150
- If you see out-of-memory errors during serving, please 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
151
152
153
```
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --mem-fraction-static 0.7
```
Yineng Zhang's avatar
Yineng Zhang committed
154
- If you see out-of-memory errors during prefill for long prompts on a model that supports long context, consider using chunked prefill.
Ying Sheng's avatar
Ying Sheng committed
155
```
Yineng Zhang's avatar
Yineng Zhang committed
156
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --chunked-prefill-size 8192
Ying Sheng's avatar
Ying Sheng committed
157
```
158
- See [hyperparameter_tuning.md](docs/en/hyperparameter_tuning.md) on tuning hyperparameters for better performance.
159
- Add `--nnodes 2` to run tensor parallelism on multiple nodes. 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.
Ying Sheng's avatar
Ying Sheng committed
160
161
```
# Node 0
162
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
163
164

# Node 1
165
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
166
```
167
- If the model does not have a template in the Hugging Face tokenizer, you can specify a [custom chat template](docs/en/custom_chat_template.md).
168
- To enable fp8 quantization, you can add `--quantization fp8` on a fp16 checkpoint or directly load a fp8 checkpoint without specifying any arguments.
169
- To enable experimental torch.compile support, you can add `--enable-torch-compile`. It accelerates small models on small batch sizes.
Lianmin Zheng's avatar
Lianmin Zheng committed
170
 
Ying Sheng's avatar
Ying Sheng committed
171
172
### Supported Models

173
- Llama / Llama 2 / Llama 3 / Llama 3.1
Ying Sheng's avatar
Ying Sheng committed
174
175
176
- Mistral / Mixtral
- Gemma / Gemma 2
- Qwen / Qwen 2 / Qwen 2 MoE
177
- DeepSeek / DeepSeek 2
Ying Sheng's avatar
Ying Sheng committed
178
- LLaVA 1.5 / 1.6
Ying Sheng's avatar
Ying Sheng committed
179
180
181
  - `python -m sglang.launch_server --model-path liuhaotian/llava-v1.5-7b --tokenizer-path llava-hf/llava-1.5-7b-hf --chat-template vicuna_v1.1 --port 30000`
  - `python -m sglang.launch_server --model-path liuhaotian/llava-v1.6-vicuna-7b --tokenizer-path llava-hf/llava-1.5-7b-hf --chat-template vicuna_v1.1 --port 30000`
  - `python -m sglang.launch_server --model-path liuhaotian/llava-v1.6-34b --tokenizer-path liuhaotian/llava-v1.6-34b-tokenizer --port 30000`
Ying Sheng's avatar
Ying Sheng committed
182
- LLaVA-NeXT-Video
Ying Sheng's avatar
Ying Sheng committed
183
  - see [examples/usage/llava_video](examples/usage/llava_video)
Ying Sheng's avatar
Ying Sheng committed
184
185
186
187
188
189
190
191
- Yi-VL
  - see [srt_example_yi_vl.py](examples/quick_start/srt_example_yi_vl.py).
- StableLM
- Command-R
- DBRX
- Grok
- ChatGLM
- InternLM 2
zhyncs's avatar
zhyncs committed
192
- Mistral NeMo
Ying Sheng's avatar
Ying Sheng committed
193

194
Instructions for supporting a new model are [here](https://github.com/sgl-project/sglang/blob/main/docs/en/model_support.md).
Ying Sheng's avatar
Ying Sheng committed
195

Lianmin Zheng's avatar
Lianmin Zheng committed
196
197
198
199
200
201
202
203
204
205
206
#### Use Models From ModelScope
To use model from [ModelScope](https://www.modelscope.cn), setting environment variable SGLANG_USE_MODELSCOPE.
```
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
```    

#### Run Llama 3.1 405B
Ying Sheng's avatar
Ying Sheng committed
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221

```bash
## 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
# replace the `172.16.4.52:20000` with your own first node ip address and port, disable CUDA Graph temporarily

# on the first node
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 --mem-frac 0.75

# on the second
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 --mem-frac 0.75
```

Ying Sheng's avatar
Ying Sheng committed
222
223
### Benchmark Performance

Ying Sheng's avatar
Ying Sheng committed
224
- 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, consider using `sglang.bench_serving`.
Ying Sheng's avatar
Ying Sheng committed
225
  ```
226
  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
227
228
229
  ```
- Benchmark online serving. Launch a server first and run the following command.
  ```
230
  python3 -m sglang.bench_serving --backend sglang --num-prompt 10
Ying Sheng's avatar
Ying Sheng committed
231
232
  ```

Ying Sheng's avatar
Ying Sheng committed
233
234
235
236
## Frontend: Structured Generation Language (SGLang)
The frontend language can be used with local models or API models.

### Quick Start
Lianmin Zheng's avatar
Lianmin Zheng committed
237
238
The example below shows how to use sglang to answer a mulit-turn question.

Ying Sheng's avatar
Ying Sheng committed
239
#### Using Local Models
240
First, launch a server with
Lianmin Zheng's avatar
Lianmin Zheng committed
241
```
Ying Sheng's avatar
Ying Sheng committed
242
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000
Lianmin Zheng's avatar
Lianmin Zheng committed
243
244
```

245
246
Then, connect to the server and answer a multi-turn question.

Lianmin Zheng's avatar
Lianmin Zheng committed
247
```python
248
from sglang import function, system, user, assistant, gen, set_default_backend, RuntimeEndpoint
Lianmin Zheng's avatar
Lianmin Zheng committed
249
250
251
252
253
254
255
256
257

@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))

258
set_default_backend(RuntimeEndpoint("http://localhost:30000"))
Lianmin Zheng's avatar
Lianmin Zheng committed
259
260
261
262
263
264
265
266

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"])
267
268

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
269
270
```

Ying Sheng's avatar
Ying Sheng committed
271
#### Using OpenAI Models
272
Set the OpenAI API Key
Lianmin Zheng's avatar
Lianmin Zheng committed
273
```
274
export OPENAI_API_KEY=sk-******
Lianmin Zheng's avatar
Lianmin Zheng committed
275
276
```

277
Then, answer a multi-turn question.
Lianmin Zheng's avatar
Lianmin Zheng committed
278
```python
279
from sglang import function, system, user, assistant, gen, set_default_backend, OpenAI
Lianmin Zheng's avatar
Lianmin Zheng committed
280
281
282
283
284
285
286
287
288

@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))

289
set_default_backend(OpenAI("gpt-3.5-turbo"))
Lianmin Zheng's avatar
Lianmin Zheng committed
290
291
292
293
294
295
296
297

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"])
298
299

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
300
301
```

Ying Sheng's avatar
Ying Sheng committed
302
#### More Examples
Lianmin Zheng's avatar
Lianmin Zheng committed
303

304
Anthropic and VertexAI (Gemini) models are also supported.
Lianmin Zheng's avatar
Lianmin Zheng committed
305
306
You can find more examples at [examples/quick_start](examples/quick_start).

Ying Sheng's avatar
Ying Sheng committed
307
### Language Feature
Lianmin Zheng's avatar
Lianmin Zheng committed
308
309
310
311
312
To begin with, import sglang.
```python
import sglang as sgl
```

Lianmin Zheng's avatar
Lianmin Zheng committed
313
`sglang` provides some simple primitives such as `gen`, `select`, `fork`, `image`.
Lianmin Zheng's avatar
Lianmin Zheng committed
314
315
You can implement your prompt flow in a function decorated by `sgl.function`.
You can then invoke the function with `run` or `run_batch`.
316
The system will manage the state, chat template, parallelism and batching for you.
Lianmin Zheng's avatar
Lianmin Zheng committed
317

318
319
The complete code for the examples below can be found at [readme_examples.py](examples/usage/readme_examples.py)

Ying Sheng's avatar
Ying Sheng committed
320
#### Control Flow
Lianmin Zheng's avatar
Lianmin Zheng committed
321
322
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
323
324
```python
@sgl.function
325
326
327
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
328
329
330

    if s["tool"] == "calculator":
        s += "The math expression is" + sgl.gen("expression")
331
332
    elif s["tool"] == "search engine":
        s += "The key word to search is" + sgl.gen("word")
Lianmin Zheng's avatar
Lianmin Zheng committed
333
```
Lianmin Zheng's avatar
Lianmin Zheng committed
334

Ying Sheng's avatar
Ying Sheng committed
335
#### Parallelism
Lianmin Zheng's avatar
Lianmin Zheng committed
336
337
338
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
339
340
341
342
343
344
345
346
```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
347
    forks = s.fork(2)
Lianmin Zheng's avatar
Lianmin Zheng committed
348
349
350
351
352
353
354
355
    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
356

Ying Sheng's avatar
Ying Sheng committed
357
#### Multi Modality
Lianmin Zheng's avatar
Lianmin Zheng committed
358
359
Use `sgl.image` to pass an image as input.

Lianmin Zheng's avatar
Lianmin Zheng committed
360
361
```python
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
362
def image_qa(s, image_file, question):
Lianmin Zheng's avatar
Lianmin Zheng committed
363
    s += sgl.user(sgl.image(image_file) + question)
Lianmin Zheng's avatar
Lianmin Zheng committed
364
    s += sgl.assistant(sgl.gen("answer", max_tokens=256)
Lianmin Zheng's avatar
Lianmin Zheng committed
365
366
```

367
368
See also [srt_example_llava.py](examples/quick_start/srt_example_llava.py).

Ying Sheng's avatar
Ying Sheng committed
369
#### Constrained Decoding
370
371
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
372

Lianmin Zheng's avatar
Lianmin Zheng committed
373
```python
Lianmin Zheng's avatar
Lianmin Zheng committed
374
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
375
376
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
377
    s += "A: " + sgl.gen(
Lianmin Zheng's avatar
Lianmin Zheng committed
378
379
380
381
382
        "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
383

Ying Sheng's avatar
Ying Sheng committed
384
#### JSON Decoding
Lianmin Zheng's avatar
Lianmin Zheng committed
385
Use `regex` to specify a JSON schema with a regular expression.
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406

```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
407
    s += name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
408
409
410
    s += sgl.gen("json_output", max_tokens=256, regex=character_regex)
```

Lianmin Zheng's avatar
Lianmin Zheng committed
411
See also [json_decode.py](examples/usage/json_decode.py) for an additional example on specifying formats with Pydantic models.
412

Ying Sheng's avatar
Ying Sheng committed
413
#### Batching
Lianmin Zheng's avatar
Lianmin Zheng committed
414
415
Use `run_batch` to run a batch of requests with continuous batching.

Lianmin Zheng's avatar
Lianmin Zheng committed
416
417
418
419
420
421
422
423
424
425
426
427
```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
428
    progress_bar=True
Lianmin Zheng's avatar
Lianmin Zheng committed
429
430
)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
431

Ying Sheng's avatar
Ying Sheng committed
432
#### Streaming
Lianmin Zheng's avatar
Lianmin Zheng committed
433
434
Add `stream=True` to enable streaming.

Lianmin Zheng's avatar
Lianmin Zheng committed
435
436
437
438
439
440
```python
@sgl.function
def text_qa(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", stop="\n")

441
state = text_qa.run(
Lianmin Zheng's avatar
Lianmin Zheng committed
442
    question="What is the capital of France?",
Lianmin Zheng's avatar
Lianmin Zheng committed
443
444
445
    temperature=0.1,
    stream=True
)
Lianmin Zheng's avatar
Lianmin Zheng committed
446

Lianmin Zheng's avatar
Lianmin Zheng committed
447
448
449
for out in state.text_iter():
    print(out, end="", flush=True)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
450

451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
#### 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
469
#### Tips and Implementation Details
470
471
- 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
472

Lianmin Zheng's avatar
Lianmin Zheng committed
473

Ying Sheng's avatar
Ying Sheng committed
474
475
476
## Benchmark And Performance
![8b_throughput](https://lmsys.org/images/blog/sglang_llama3/8b_throughput.svg)
![70b_fp8_throughput](https://lmsys.org/images/blog/sglang_llama3/70b_fp8_throughput.svg)
Lianmin Zheng's avatar
Lianmin Zheng committed
477

Ying Sheng's avatar
Ying Sheng committed
478
Learn more at this [blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/).
Lianmin Zheng's avatar
Lianmin Zheng committed
479

Lianmin Zheng's avatar
Lianmin Zheng committed
480
## Roadmap
Ying Sheng's avatar
Ying Sheng committed
481
[Development Roadmap (2024 Q3)](https://github.com/sgl-project/sglang/issues/634)
Lianmin Zheng's avatar
Lianmin Zheng committed
482
483

## Citation And Acknowledgment
Ying Sheng's avatar
Ying Sheng committed
484
485
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).