README.md 15.7 KB
Newer Older
Lianmin Zheng's avatar
Lianmin Zheng committed
1
2
3
4
5
6
<div align="center">
<img src="assets/logo.png" alt="logo" width="400"></img>
</div>

--------------------------------------------------------------------------------

7
| [**Blog**](https://lmsys.org/blog/2024-01-17-sglang/) | [**Paper**](https://arxiv.org/abs/2312.07104) |
Lianmin Zheng's avatar
Lianmin Zheng committed
8

Ying Sheng's avatar
Ying Sheng committed
9
10
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
11

12
The core features include:
Ying Sheng's avatar
Ying Sheng committed
13
- **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
14
- **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
15

Ying Sheng's avatar
Ying Sheng committed
16
## News
Ying Sheng's avatar
Ying Sheng committed
17
- [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/)).
Lianmin Zheng's avatar
Lianmin Zheng committed
18
19
- [2024/02] 🔥 SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
- [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
20

Ying Sheng's avatar
Ying Sheng committed
21
22
23
24
25
26
27
<details>
<summary>More</summary>

- [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
28
29
30
## Contents
- [Install](#install)
- [Backend: SGLang Runtime (SRT)](#backend-sglang-runtime-srt)
Ying Sheng's avatar
Ying Sheng committed
31
- [Frontend: Structured Generation Language (SGLang)](#frontend-structured-generation-language-sglang)
Lianmin Zheng's avatar
Lianmin Zheng committed
32
33
34
35
36
37
- [Benchmark And Performance](#benchmark-and-performance)
- [Roadmap](#roadmap)
- [Citation And Acknowledgment](#citation-and-acknowledgment)

## Install

Lianmin Zheng's avatar
Lianmin Zheng committed
38
39
40
### Method 1: With pip
```
pip install "sglang[all]"
Lianmin Zheng's avatar
Lianmin Zheng committed
41

Lianmin Zheng's avatar
Lianmin Zheng committed
42
43
44
# Install FlashInfer CUDA kernels
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
```
45

Lianmin Zheng's avatar
Lianmin Zheng committed
46
### Method 2: From source
Lianmin Zheng's avatar
Lianmin Zheng committed
47
```
48
git clone https://github.com/sgl-project/sglang.git
Lianmin Zheng's avatar
Lianmin Zheng committed
49
50
51
52
cd sglang

pip install -e "python[all]"

Lianmin Zheng's avatar
Lianmin Zheng committed
53
54
55
# Install FlashInfer CUDA kernels
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
```
56

Lianmin Zheng's avatar
Lianmin Zheng committed
57
58
### Method 3: Using docker
The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags).
Ying Sheng's avatar
Ying Sheng committed
59

Liangsheng Yin's avatar
Liangsheng Yin committed
60
61
62
63
64
65
66
67
68
69
```bash
docker run --gpus all \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B --host 0.0.0.0 --port 30000
```

Lianmin Zheng's avatar
Lianmin Zheng committed
70
### Common Notes
71
72
73
74
75
- If you see errors from the Triton compiler, please install the [Triton Nightly](https://triton-lang.org/main/getting-started/installation.html) by
```
pip uninstall -y triton triton-nightly
pip install -U --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/ triton-nightly
```
Lianmin Zheng's avatar
Lianmin Zheng committed
76
77
- 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
78

Ying Sheng's avatar
Ying Sheng committed
79
80
81
## Backend: SGLang Runtime (SRT)
The SGLang Runtime (SRT) is an efficient serving engine.

Ying Sheng's avatar
Ying Sheng committed
82
### Quick Start
Ying Sheng's avatar
Ying Sheng committed
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
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](docs/sampling_params.md).

### 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
132
It supports streaming, vision, and most features of the Chat/Completions/Models endpoints specified by the [OpenAI API Reference](https://platform.openai.com/docs/api-reference/).
Ying Sheng's avatar
Ying Sheng committed
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164

### 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
```
- 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`
```
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --mem-fraction-static 0.7
```
- See [hyperparameter_tuning.md](docs/hyperparameter_tuning.md) on tuning hyperparameters for better performance.
- 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-1` be the hostname of the first node and `50000` be an available port.
```
# Node 0
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-1:50000 --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-1:50000 --nnodes 2 --node-rank 1
```
- If the model does not have a template in the Hugging Face tokenizer, you can specify a [custom chat template](docs/custom_chat_template.md).

### Supported Models

- Llama / Llama 2 / Llama 3
- Mistral / Mixtral
- Gemma / Gemma 2
- Qwen / Qwen 2 / Qwen 2 MoE
- LLaVA 1.5 / 1.6
Ying Sheng's avatar
Ying Sheng committed
165
166
167
  - `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
168
- LLaVA-NeXT-Video
Ying Sheng's avatar
Ying Sheng committed
169
  - see [examples/usage/llava_video](examples/usage/llava_video)
Ying Sheng's avatar
Ying Sheng committed
170
171
172
173
174
175
176
177
178
179
180
- Yi-VL
  - see [srt_example_yi_vl.py](examples/quick_start/srt_example_yi_vl.py).
- StableLM
- Command-R
- DBRX
- Grok
- ChatGLM
- InternLM 2

Instructions for supporting a new model are [here](https://github.com/sgl-project/sglang/blob/main/docs/model_support.md).

Ying Sheng's avatar
Ying Sheng committed
181
182
183
184
185
186
187
188
189
190
191
### Benchmark Performance

- Benchmark a single static batch. Run the following command without launching a server. The arguments are the same as those for `launch_server.py`.
  ```
  python -m sglang.bench_latency --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 32 --input-len 256 --output-len 32
  ```
- Benchmark online serving. Launch a server first and run the following command.
  ```
  python3 -m sglang.bench_serving --backend sglang --num-prompt 10
  ```

Ying Sheng's avatar
Ying Sheng committed
192
193
194
195
## 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
196
197
The example below shows how to use sglang to answer a mulit-turn question.

Ying Sheng's avatar
Ying Sheng committed
198
#### Using Local Models
199
First, launch a server with
Lianmin Zheng's avatar
Lianmin Zheng committed
200
```
Ying Sheng's avatar
Ying Sheng committed
201
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000
Lianmin Zheng's avatar
Lianmin Zheng committed
202
203
```

204
205
Then, connect to the server and answer a multi-turn question.

Lianmin Zheng's avatar
Lianmin Zheng committed
206
```python
207
from sglang import function, system, user, assistant, gen, set_default_backend, RuntimeEndpoint
Lianmin Zheng's avatar
Lianmin Zheng committed
208
209
210
211
212
213
214
215
216

@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))

217
set_default_backend(RuntimeEndpoint("http://localhost:30000"))
Lianmin Zheng's avatar
Lianmin Zheng committed
218
219
220
221
222
223
224
225

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"])
226
227

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
228
229
```

Ying Sheng's avatar
Ying Sheng committed
230
#### Using OpenAI Models
231
Set the OpenAI API Key
Lianmin Zheng's avatar
Lianmin Zheng committed
232
```
233
export OPENAI_API_KEY=sk-******
Lianmin Zheng's avatar
Lianmin Zheng committed
234
235
```

236
Then, answer a multi-turn question.
Lianmin Zheng's avatar
Lianmin Zheng committed
237
```python
238
from sglang import function, system, user, assistant, gen, set_default_backend, OpenAI
Lianmin Zheng's avatar
Lianmin Zheng committed
239
240
241
242
243
244
245
246
247

@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))

248
set_default_backend(OpenAI("gpt-3.5-turbo"))
Lianmin Zheng's avatar
Lianmin Zheng committed
249
250
251
252
253
254
255
256

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"])
257
258

print(state["answer_1"])
Lianmin Zheng's avatar
Lianmin Zheng committed
259
260
```

Ying Sheng's avatar
Ying Sheng committed
261
#### More Examples
Lianmin Zheng's avatar
Lianmin Zheng committed
262

263
Anthropic and VertexAI (Gemini) models are also supported.
Lianmin Zheng's avatar
Lianmin Zheng committed
264
265
You can find more examples at [examples/quick_start](examples/quick_start).

Ying Sheng's avatar
Ying Sheng committed
266
### Language Feature
Lianmin Zheng's avatar
Lianmin Zheng committed
267
268
269
270
271
To begin with, import sglang.
```python
import sglang as sgl
```

Lianmin Zheng's avatar
Lianmin Zheng committed
272
`sglang` provides some simple primitives such as `gen`, `select`, `fork`, `image`.
Lianmin Zheng's avatar
Lianmin Zheng committed
273
274
You can implement your prompt flow in a function decorated by `sgl.function`.
You can then invoke the function with `run` or `run_batch`.
275
The system will manage the state, chat template, parallelism and batching for you.
Lianmin Zheng's avatar
Lianmin Zheng committed
276

277
278
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
279
#### Control Flow
Lianmin Zheng's avatar
Lianmin Zheng committed
280
281
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
282
283
```python
@sgl.function
284
285
286
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
287
288
289

    if s["tool"] == "calculator":
        s += "The math expression is" + sgl.gen("expression")
290
291
    elif s["tool"] == "search engine":
        s += "The key word to search is" + sgl.gen("word")
Lianmin Zheng's avatar
Lianmin Zheng committed
292
```
Lianmin Zheng's avatar
Lianmin Zheng committed
293

Ying Sheng's avatar
Ying Sheng committed
294
#### Parallelism
Lianmin Zheng's avatar
Lianmin Zheng committed
295
296
297
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
298
299
300
301
302
303
304
305
```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
306
    forks = s.fork(2)
Lianmin Zheng's avatar
Lianmin Zheng committed
307
308
309
310
311
312
313
314
    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
315

Ying Sheng's avatar
Ying Sheng committed
316
#### Multi Modality
Lianmin Zheng's avatar
Lianmin Zheng committed
317
318
Use `sgl.image` to pass an image as input.

Lianmin Zheng's avatar
Lianmin Zheng committed
319
320
```python
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
321
def image_qa(s, image_file, question):
Lianmin Zheng's avatar
Lianmin Zheng committed
322
    s += sgl.user(sgl.image(image_file) + question)
Lianmin Zheng's avatar
Lianmin Zheng committed
323
    s += sgl.assistant(sgl.gen("answer", max_tokens=256)
Lianmin Zheng's avatar
Lianmin Zheng committed
324
325
```

326
327
See also [srt_example_llava.py](examples/quick_start/srt_example_llava.py).

Ying Sheng's avatar
Ying Sheng committed
328
#### Constrained Decoding
329
330
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
331

Lianmin Zheng's avatar
Lianmin Zheng committed
332
```python
Lianmin Zheng's avatar
Lianmin Zheng committed
333
@sgl.function
Lianmin Zheng's avatar
Lianmin Zheng committed
334
335
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
336
    s += "A: " + sgl.gen(
Lianmin Zheng's avatar
Lianmin Zheng committed
337
338
339
340
341
        "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
342

Ying Sheng's avatar
Ying Sheng committed
343
#### JSON Decoding
Lianmin Zheng's avatar
Lianmin Zheng committed
344
Use `regex` to specify a JSON schema with a regular expression.
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365

```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
366
    s += name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
367
368
369
    s += sgl.gen("json_output", max_tokens=256, regex=character_regex)
```

Lianmin Zheng's avatar
Lianmin Zheng committed
370
See also [json_decode.py](examples/usage/json_decode.py) for an additional example on specifying formats with Pydantic models.
371

Ying Sheng's avatar
Ying Sheng committed
372
#### Batching
Lianmin Zheng's avatar
Lianmin Zheng committed
373
374
Use `run_batch` to run a batch of requests with continuous batching.

Lianmin Zheng's avatar
Lianmin Zheng committed
375
376
377
378
379
380
381
382
383
384
385
386
```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
387
    progress_bar=True
Lianmin Zheng's avatar
Lianmin Zheng committed
388
389
)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
390

Ying Sheng's avatar
Ying Sheng committed
391
#### Streaming
Lianmin Zheng's avatar
Lianmin Zheng committed
392
393
Add `stream=True` to enable streaming.

Lianmin Zheng's avatar
Lianmin Zheng committed
394
395
396
397
398
399
```python
@sgl.function
def text_qa(s, question):
    s += "Q: " + question + "\n"
    s += "A:" + sgl.gen("answer", stop="\n")

400
state = text_qa.run(
Lianmin Zheng's avatar
Lianmin Zheng committed
401
    question="What is the capital of France?",
Lianmin Zheng's avatar
Lianmin Zheng committed
402
403
404
    temperature=0.1,
    stream=True
)
Lianmin Zheng's avatar
Lianmin Zheng committed
405

Lianmin Zheng's avatar
Lianmin Zheng committed
406
407
408
for out in state.text_iter():
    print(out, end="", flush=True)
```
Lianmin Zheng's avatar
Lianmin Zheng committed
409

Ying Sheng's avatar
Ying Sheng committed
410
#### Tips and Implementation Details
411
412
- 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
413

Lianmin Zheng's avatar
Lianmin Zheng committed
414
## Benchmark And Performance
Lianmin Zheng's avatar
Lianmin Zheng committed
415
416
417
418
419
420
- Llama-7B on NVIDIA A10G, FP16, Tensor Parallelism=1
![llama_7b](assets/llama_7b.jpg)

- Mixtral-8x7B on NVIDIA A10G, FP16, Tensor Parallelism=8
![mixtral_8x7b](assets/mixtral_8x7b.jpg)

Lianmin Zheng's avatar
Lianmin Zheng committed
421
422
- Learn more about the above [results](docs/benchmark_results.md).
- Synthetic latency and throughput benchmark [scripts](https://github.com/sgl-project/sglang/tree/main/benchmark/latency_throughput).
Lianmin Zheng's avatar
Lianmin Zheng committed
423

Lianmin Zheng's avatar
Lianmin Zheng committed
424
## Roadmap
Ying Sheng's avatar
Ying Sheng committed
425
[Development Roadmap (2024 Q3)](https://github.com/sgl-project/sglang/issues/634)
Lianmin Zheng's avatar
Lianmin Zheng committed
426
427

## Citation And Acknowledgment
Ying Sheng's avatar
Ying Sheng committed
428
429
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).