mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
29 lines
806 B
Python
29 lines
806 B
Python
from tensorrt_llm import SamplingParams
|
|
from tensorrt_llm._tensorrt_engine import LLM
|
|
|
|
|
|
def main():
|
|
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
|
|
|
|
# Alternatively, use "nvidia/Llama-3.1-8B-Instruct-FP8" to enable FP8 inference.
|
|
llm = LLM(model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
|
|
|
|
outputs = llm.generate(prompts, sampling_params)
|
|
|
|
# Print the outputs.
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
generated_text = output.outputs[0].text
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
|
|
|
|
|
# The entry point of the program need to be protected for spawning processes.
|
|
if __name__ == '__main__':
|
|
main()
|