Offline Inference With Profiler

Source: examples/offline_inference_with_profiler.py.

import os
import time

from vllm import LLM, SamplingParams

# enable torch profiler, can also be set on cmd line
os.environ["VLLM_TORCH_PROFILER_DIR"] = "./vllm_profile"

# 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)

if __name__ == "__main__":

    # Create an LLM.
    llm = LLM(model="facebook/opt-125m", tensor_parallel_size=1)

    llm.start_profile()

    # 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)

    llm.stop_profile()

    # 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}")

    # Add a buffer to wait for profiler in the background process
    # (in case MP is on) to finish writing profiling output.
    time.sleep(10)