Cpu 卸载#
源代码 vllm-project/vllm。
1from vllm import LLM, SamplingParams
2
3# Sample prompts.
4prompts = [
5 "Hello, my name is",
6 "The president of the United States is",
7 "The capital of France is",
8 "The future of AI is",
9]
10# Create a sampling params object.
11sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
12
13# Create an LLM.
14llm = LLM(model="meta-llama/Llama-2-13b-chat-hf", cpu_offload_gb=10)
15# Generate texts from the prompts. The output is a list of RequestOutput objects
16# that contain the prompt, generated text, and other information.
17outputs = llm.generate(prompts, sampling_params)
18# Print the outputs.
19for output in outputs:
20 prompt = output.prompt
21 generated_text = output.outputs[0].text
22 print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")