| if __name__ == '__main__': | |
| from vllm import LLM, SamplingParams | |
| prompts = [ | |
| "Hello, my name is", | |
| ] | |
| sampling_params = SamplingParams(temperature=0.6, top_p=0.95) | |
| model_name = "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound" | |
| llm = LLM(model=model_name, tensor_parallel_size=1,enforce_eager=True) | |
| outputs = llm.generate(prompts, sampling_params) | |
| for output in outputs: | |
| prompt = output.prompt | |
| generated_text = output.outputs[0].text | |
| print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") | |