Generate text#
Source NVIDIA/TensorRT-LLM.
1from tensorrt_llm import LLM, SamplingParams
2
3
4def main():
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.
8 llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
9
10 # Sample prompts.
11 prompts = [
12 "Hello, my name is",
13 "The president of the United States is",
14 "The capital of France is",
15 "The future of AI is",
16 ]
17
18 # Create a sampling params.
19 sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
20
21 for output in llm.generate(prompts, sampling_params):
22 print(
23 f"Prompt: {output.prompt!r}, Generated text: {output.outputs[0].text!r}"
24 )
25
26 # Got output like
27 # 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'
28 # 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'
29 # Prompt: 'The capital of France is', Generated text: 'Paris.'
30 # 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'
31
32
33if __name__ == '__main__':
34 main()