# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

import argparse
from vllm import LLM, SamplingParams

# Sample prompts.
prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
    "Hello, my name is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)


def main(model_path, tensor_parallel_size, gpu_memory_utilization, dtype):
    # Create an LLM.
    llm = LLM(model=model_path, tensor_parallel_size=tensor_parallel_size, dtype=dtype,
              trust_remote_code=True, enforce_eager=True, block_size=64,
              enable_prefix_caching=False, gpu_memory_utilization=gpu_memory_utilization)
    # Generate texts from the prompts.
    # The output is a list of RequestOutput objects
    # that contain the prompt, generated text, and other information.
    outputs = llm.generate(prompts, sampling_params)
    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt:    {prompt!r}")
        print(f"Output:    {generated_text!r}")
        print("-" * 60)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="vLLM Offline Inference Example")
    parser.add_argument("--model_path", type=str, default="/mnt/data/llm-models/qwen3/Qwen3-8B",
                        help="Path to the model")
    parser.add_argument("--tp", "--tensor_parallel_size", type=int, default=1,
                        help="Tensor parallel size")
    parser.add_argument("--gpu_memory_utilization", type=float, default=0.98,
                        help="GPU memory utilization (0.0-1.0)")
    parser.add_argument("--dtype", type=str, default="float16",
                        choices=["float16", "float32", "int8", "auto"],
                        help="Data type for model weights")

    args = parser.parse_args()
    main(args.model_path, args.tensor_parallel_size, args.gpu_memory_utilization, args.dtype)