Qwen2.5-VL-7B-Instruct-FP8

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="nvidia/Qwen2.5-VL-7B-Instruct-FP8", tensor_parallel_size=4)

    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 needs to be protected for spawning processes.
if __name__ == '__main__':
    main()