1importasyncio 2 3fromtensorrt_llmimportLLM,SamplingParams 4 5 6defmain(): 7# model could accept HF model name or a path to local HF model. 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)1920# Async based on Python coroutines21asyncdeftask(prompt:str):22output=awaitllm.generate_async(prompt,sampling_params)23print(24f"Prompt:{output.prompt!r}, Generated text:{output.outputs[0].text!r}"25)2627asyncdefmain():28tasks=[task(prompt)forpromptinprompts]29awaitasyncio.gather(*tasks)3031asyncio.run(main())3233# Got output like follows:34# 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'35# Prompt: 'The capital of France is', Generated text: 'Paris.'36# 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'373839if__name__=='__main__':40main()