haotian-liu/sglang_contrib

pip install "sglang[all]"

git clone [email protected]:sgl-project/sglang.git
cd sglang

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

export OPENAI_API_KEY=sk-******

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"])

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000

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"])

import sglang as sgl

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

    if s["tool"] == "calculator":
        s += "The math expression is" + sgl.gen("expression")
    elif s["tool"] == "web browser":
        s += "The website url is" + sgl.gen("url")

@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")

@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)

@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?)",
    )

@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
)

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

states = 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)

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000

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

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)

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --chat-template llama-2

{
  "name": "my_model",
  "system": "<|im_start|>system",
  "user": "<|im_start|>user",
  "assistant": "<|im_start|>assistant",
  "sep_style": "CHATML",
  "sep": "<|im_end|>",
  "stop_str": ["<|im_end|>", "<|im_start|>"]
}

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --chat-template ./my_model_template.json

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --tp 2

python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --mem-fraction-static 0.7

@misc{zheng2023efficiently,
      title={Efficiently Programming Large Language Models using SGLang},
      author={Lianmin Zheng and Liangsheng Yin and Zhiqiang Xie and Jeff Huang and Chuyue Sun and Cody Hao Yu and Shiyi Cao and Christos Kozyrakis and Ion Stoica and Joseph E. Gonzalez and Clark Barrett and Ying Sheng},
      year={2023},
      eprint={2312.07104},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}