TensorRT-LLM 快速入门指南

目录

TensorRT-LLM 快速入门指南#

LLM API#

LLM API 是 Python API，旨在直接在 Python 中简化 TensorRT-LLM 的设置和推理。它通过简单地指定 HuggingFace 仓库名称或模型检查点来启用模型优化。LLM API 通过管理检查点转换、引擎构建、引擎加载和模型推理，简化了整个流程，所有这些功能都通过单一的 Python 对象实现。

from tensorrt_llm import LLM, SamplingParams


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(temperature=0.8, top_p=0.95)

    llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")

    outputs = llm.generate(prompts, sampling_params)

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


# The entry point of the program need to be protected for spawning processes.
if __name__ == '__main__':
    main()
目录