1fromtensorrt_llmimportLLM,SamplingParams 2 3 4defmain(): 5 6# Model could accept HF model name, a path to local HF model, 7# or TensorRT Model Optimizer's quantized checkpoints like nvidia/Llama-3.1-8B-Instruct-FP8 on HF. 8llm=LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0") 910# Sample prompts.11prompts=[12"Hello, my name is",13"The capital of France is",14"The future of AI is",15]1617# Create a sampling params.18sampling_params=SamplingParams(temperature=0.8,top_p=0.95)1920foroutputinllm.generate(prompts,sampling_params):21print(22f"Prompt:{output.prompt!r}, Generated text:{output.outputs[0].text!r}"23)2425# Got output like26# Prompt: 'Hello, my name is', Generated text: '\n\nJane Smith. I am a student pursuing my degree in Computer Science at [university]. I enjoy learning new things, especially technology and programming'27# Prompt: 'The president of the United States is', Generated text: 'likely to nominate a new Supreme Court justice to fill the seat vacated by the death of Antonin Scalia. The Senate should vote to confirm the'28# Prompt: 'The capital of France is', Generated text: 'Paris.'29# Prompt: 'The future of AI is', Generated text: 'an exciting time for us. We are constantly researching, developing, and improving our platform to create the most advanced and efficient model available. We are'303132if__name__=='__main__':33main()