Sampling Parameters

# Use model-provided defaults from generation_config.json (default behavior)
python -m sglang.launch_server --model-path <MODEL> --sampling-defaults model

# Use SGLang/OpenAI constant defaults instead
python -m sglang.launch_server --model-path <MODEL> --sampling-defaults openai

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

import requests

response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "The capital of France is",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 32,
        },
    },
)
print(response.json())

import requests, json

response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "The capital of France is",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 32,
        },
        "stream": True,
    },
    stream=True,
)

prev = 0
for chunk in response.iter_lines(decode_unicode=False):
    chunk = chunk.decode("utf-8")
    if chunk and chunk.startswith("data:"):
        if chunk == "data: [DONE]":
            break
        data = json.loads(chunk[5:].strip("\n"))
        output = data["text"].strip()
        print(output[prev:], end="", flush=True)
        prev = len(output)
print("")

python3 -m sglang.launch_server --model-path lmms-lab/llava-onevision-qwen2-7b-ov

curl -o example_image.png -L https://github.com/sgl-project/sglang/blob/main/examples/assets/example_image.png?raw=true

import requests

response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"
                "<|im_start|>user\n<image>\nDescribe this image in a very short sentence.<|im_end|>\n"
                "<|im_start|>assistant\n",
        "image_data": "example_image.png",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 32,
        },
    },
)
print(response.json())

python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \
--port 30000 --host 0.0.0.0 --grammar-backend [xgrammar|outlines] # xgrammar or outlines (default: xgrammar)

import json
import requests

json_schema = json.dumps({
    "type": "object",
    "properties": {
        "name": {"type": "string", "pattern": "^[\\w]+$"},
        "population": {"type": "integer"},
    },
    "required": ["name", "population"],
})

# JSON (works with both Outlines and XGrammar)
response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "Here is the information of the capital of France in the JSON format.\n",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 64,
            "json_schema": json_schema,
        },
    },
)
print(response.json())

# Regular expression (Outlines backend only)
response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "Paris is the capital of",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 64,
            "regex": "(France|England)",
        },
    },
)
print(response.json())

# EBNF (XGrammar backend only)
response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "Write a greeting.",
        "sampling_params": {
            "temperature": 0,
            "max_new_tokens": 64,
            "ebnf": 'root ::= "Hello" | "Hi" | "Hey"',
        },
    },
)
print(response.json())

python -m sglang.launch_server \
  --model-path meta-llama/Meta-Llama-3-8B-Instruct \
  --port 30000 \
  --enable-custom-logit-processor

from sglang.srt.sampling.custom_logit_processor import CustomLogitProcessor

class DeterministicLogitProcessor(CustomLogitProcessor):
    """A dummy logit processor that changes the logits to always
    sample the given token id.
    """

    def __call__(self, logits, custom_param_list):
        # Check that the number of logits matches the number of custom parameters
        assert logits.shape[0] == len(custom_param_list)
        key = "token_id"

        for i, param_dict in enumerate(custom_param_list):
            # Mask all other tokens
            logits[i, :] = -float("inf")
            # Assign highest probability to the specified token
            logits[i, param_dict[key]] = 0.0
        return logits

import requests

response = requests.post(
    "http://localhost:30000/generate",
    json={
        "text": "The capital of France is",
        "custom_logit_processor": DeterministicLogitProcessor().to_str(),
        "sampling_params": {
            "temperature": 0.0,
            "max_new_tokens": 32,
            "custom_params": {"token_id": 5},
        },
    },
)
print(response.json())

import openai
from sglang.utils import print_highlight

client = openai.Client(base_url="http://127.0.0.1:30000/v1", api_key="None")

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "user", "content": "List 3 countries and their capitals."},
    ],
    temperature=0.0,
    max_tokens=32,
    extra_body={
        "custom_logit_processor": DeterministicLogitProcessor().to_str(),
        "custom_params": {"token_id": 5},
    },
)

print_highlight(f"Response: {response}")