forked from EngineX-Cambricon/enginex-mlu370-vllm
25 lines
852 B
Python
25 lines
852 B
Python
from vllm import LLM, SamplingParams
|
|
|
|
# Sample prompts.
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The president of the United States is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
# Create a sampling params object.
|
|
sampling_params = SamplingParams(temperature=0, top_p=1, n=4,use_beam_search=True)
|
|
|
|
# Create an LLM.
|
|
llm = LLM(model="/data/AE/llm/models/Llama-2-7b-hf", enforce_eager=True, dtype='float16')
|
|
# Generate texts from the prompts. The output is a list of RequestOutput objects
|
|
# that contain the prompt, generated text, and other information.
|
|
outputs = llm.generate(prompts, sampling_params)
|
|
# Print the outputs.
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
print(f"Prompt: {prompt!r}")
|
|
for out_idx in output.outputs:
|
|
generated_text = out_idx.text
|
|
print(f"Generated text: {generated_text!r}")
|