1fromtensorrt_llmimportBuildConfig,SamplingParams 2fromtensorrt_llm._tensorrt_engineimportLLM# NOTE the change 3 4 5defmain(): 6 7build_config=BuildConfig() 8build_config.max_batch_size=256 9build_config.max_num_tokens=10241011# Model could accept HF model name, a path to local HF model,12# or TensorRT Model Optimizer's quantized checkpoints like nvidia/Llama-3.1-8B-Instruct-FP8 on HF.13llm=LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",14build_config=build_config)1516# Sample prompts.17prompts=[18"Hello, my name is",19"The capital of France is",20"The future of AI is",21]2223# Create a sampling params.24sampling_params=SamplingParams(temperature=0.8,top_p=0.95)2526foroutputinllm.generate(prompts,sampling_params):27print(28f"Prompt:{output.prompt!r}, Generated text:{output.outputs[0].text!r}"29)3031# Got output like32# 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'33# 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'34# Prompt: 'The capital of France is', Generated text: 'Paris.'35# 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'363738if__name__=='__main__':39main()