from tensorrt_llm import SamplingParams
from tensorrt_llm._torch import LLM


def main():
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]
    sampling_params = SamplingParams(max_tokens=32)

    llm = LLM(model='TinyLlama/TinyLlama-1.1B-Chat-v1.0')
    outputs = llm.generate(prompts, sampling_params)

    for i, output in enumerate(outputs):
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"[{i}] Prompt: {prompt!r}, Generated text: {generated_text!r}")


if __name__ == '__main__':
    main()