sglang/docs/backend/offline_engine_api.ipynb

Offline Engine API

SGLang provides a direct inference engine without the need for an HTTP server, especially for use cases where additional HTTP server adds unnecessary complexity or overhead. Here are two general use cases:

• Offline Batch Inference
• Custom Server on Top of the Engine

This document focuses on the offline batch inference, demonstrating four different inference modes:

• Non-streaming synchronous generation
• Streaming synchronous generation
• Non-streaming asynchronous generation
• Streaming asynchronous generation

Additionally, you can easily build a custom server on top of the SGLang offline engine. A detailed example working in a python script can be found in custom_server.

Advanced Usage

The engine supports vlm inference as well as extracting hidden states.

Please see the examples for further use cases.

Offline Batch Inference

SGLang offline engine supports batch inference with efficient scheduling.

In [ ]:

# launch the offline engine
import asyncio
import io
import os

from PIL import Image
import requests
import sglang as sgl

from sglang.srt.conversation import chat_templates
from sglang.test.test_utils import is_in_ci
from sglang.utils import async_stream_and_merge, stream_and_merge

if is_in_ci():
    import patch


llm = sgl.Engine(model_path="meta-llama/Meta-Llama-3.1-8B-Instruct")

Non-streaming Synchronous Generation

In [ ]:

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}

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

Streaming Synchronous Generation

In [ ]:

prompts = [
    "Write a short, neutral self-introduction for a fictional character. Hello, my name is",
    "Provide a concise factual statement about France’s capital city. The capital of France is",
    "Explain possible future trends in artificial intelligence. The future of AI is",
]

sampling_params = {
    "temperature": 0.2,
    "top_p": 0.9,
}

print("\n=== Testing synchronous streaming generation with overlap removal ===\n")

for prompt in prompts:
    print(f"Prompt: {prompt}")
    merged_output = stream_and_merge(llm, prompt, sampling_params)
    print("Generated text:", merged_output)
    print()

Non-streaming Asynchronous Generation

In [ ]:

prompts = [
    "Write a short, neutral self-introduction for a fictional character. Hello, my name is",
    "Provide a concise factual statement about France’s capital city. The capital of France is",
    "Explain possible future trends in artificial intelligence. The future of AI is",
]

sampling_params = {"temperature": 0.8, "top_p": 0.95}

print("\n=== Testing asynchronous batch generation ===")


async def main():
    outputs = await llm.async_generate(prompts, sampling_params)

    for prompt, output in zip(prompts, outputs):
        print(f"\nPrompt: {prompt}")
        print(f"Generated text: {output['text']}")


asyncio.run(main())

Streaming Asynchronous Generation

In [ ]:

prompts = [
    "Write a short, neutral self-introduction for a fictional character. Hello, my name is",
    "Provide a concise factual statement about France’s capital city. The capital of France is",
    "Explain possible future trends in artificial intelligence. The future of AI is",
]

sampling_params = {"temperature": 0.8, "top_p": 0.95}

print("\n=== Testing asynchronous streaming generation (no repeats) ===")


async def main():
    for prompt in prompts:
        print(f"\nPrompt: {prompt}")
        print("Generated text: ", end="", flush=True)

        # Replace direct calls to async_generate with our custom overlap-aware version
        async for cleaned_chunk in async_stream_and_merge(llm, prompt, sampling_params):
            print(cleaned_chunk, end="", flush=True)

        print()  # New line after each prompt


asyncio.run(main())

In [ ]:

llm.shutdown()