Qwen1.5-7b_single_dcu_inference.py

from vllm import LLM, SamplingParams
# Sample prompts.
prompts = [
    "The capital of France is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95,top_k=50,stop="</s>")

# Create an LLM.
llm = LLM(model="./qwen2/Qwen1.5-7B-Chat",trust_remote_code=True,dtype="float16", enforce_eager=True)
# 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}")