RolloutEngine

from rllm.engine.rollout import RolloutEngine

output = await engine.get_model_response(
    messages=[{"role": "user", "content": "Hello"}],
    application_id="task_0",
    temperature=0.7,
    max_tokens=2048
)

await engine.wake_up()

await engine.sleep()

from rllm.engine.rollout import ModelOutput

# Serialize
output_dict = model_output.to_dict()

# Deserialize
model_output = ModelOutput.from_dict(output_dict)

from rllm.engine.rollout import OpenAIEngine

engine = OpenAIEngine(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",
    model="Qwen/Qwen3-4B"
)

import asyncio
from rllm.engine.rollout import OpenAIEngine

engine = OpenAIEngine(
    base_url="http://localhost:4000/v1",
    api_key="EMPTY",
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
)

async def generate():
    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
    
    output = await engine.get_model_response(
        messages,
        temperature=0.7,
        max_tokens=512
    )
    
    print(f"Content: {output.content}")
    print(f"Reasoning: {output.reasoning}")
    print(f"Tokens: {output.completion_length}")
    print(f"Finish reason: {output.finish_reason}")

asyncio.run(generate())

import asyncio
from rllm.engine.rollout import OpenAIEngine

engine = OpenAIEngine(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY",
    model="Qwen/Qwen3-4B"
)

async def generate_batch():
    tasks = [
        [{"role": "user", "content": "What is 2+2?"}],
        [{"role": "user", "content": "What is the speed of light?"}],
        [{"role": "user", "content": "Who wrote Romeo and Juliet?"}]
    ]
    
    # Generate concurrently
    results = await asyncio.gather(*[
        engine.get_model_response(messages, application_id=f"task_{i}")
        for i, messages in enumerate(tasks)
    ])
    
    for i, output in enumerate(results):
        print(f"\nTask {i}:")
        print(f"Response: {output.content}")

asyncio.run(generate_batch())