2025-02-02 14:58:18 -05:00
|
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
|
|
2024-07-17 20:54:35 -07:00
|
|
|
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=0.8, top_p=0.95)
|
|
|
|
|
|
|
|
|
|
# Create an LLM.
|
|
|
|
|
llm = LLM(model="meta-llama/Llama-2-13b-chat-hf", cpu_offload_gb=10)
|
|
|
|
|
# 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
|
|
|
|
|
generated_text = output.outputs[0].text
|
|
|
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
