自动前缀缓存

examples/offline_inference/automatic_prefix_caching.py

# SPDX-License-Identifier: Apache-2.0
"""
Demonstration script for Automatic Prefix Caching (APC) in vLLM.

Automatic Prefix Caching (APC) allows the vLLM engine to reuse cached
KV (key-value) pairs from previous prompts if a new query shares the same
prefix. This reduces redundant computation and improves inference speed.

To enable APC, set `enable_prefix_caching=True` when initializing the
vLLM engine.

This script uses a long Markdown table as the shared prompt prefix and
compares the generation time for two queries that share the same prefix
but ask different questions.

Run:
python examples/offline_inference/automatic_prefix_caching.py
"""

import time

from vllm import LLM, SamplingParams

# ruff: noqa: E501
# A prompt containing a large markdown table. The table is randomly generated by GPT-4.
LONG_PROMPT = (
    "You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as follows.\n# Table\n"
    + """
| ID  | Name          | Age | Occupation    | Country       | Email                  | Phone Number   | Address                       |
|-----|---------------|-----|---------------|---------------|------------------------|----------------|------------------------------|
| 1   | John Doe      | 29  | Engineer      | USA           | [email protected]   | 555-1234       | 123 Elm St, Springfield, IL  |
| 2   | Jane Smith    | 34  | Doctor        | Canada        | [email protected] | 555-5678       | 456 Oak St, Toronto, ON      |
| 3   | Alice Johnson | 27  | Teacher       | UK            | [email protected]    | 555-8765       | 789 Pine St, London, UK      |
| 4   | Bob Brown     | 45  | Artist        | Australia     | [email protected]      | 555-4321       | 321 Maple St, Sydney, NSW    |
| 5   | Carol White   | 31  | Scientist     | New Zealand   | [email protected]    | 555-6789       | 654 Birch St, Wellington, NZ |
| 6   | Dave Green    | 28  | Lawyer        | Ireland       | [email protected]     | 555-3456       | 987 Cedar St, Dublin, IE     |
| 7   | Emma Black    | 40  | Musician      | USA           | [email protected]     | 555-1111       | 246 Ash St, New York, NY     |
| 8   | Frank Blue    | 37  | Chef          | Canada        | [email protected]    | 555-2222       | 135 Spruce St, Vancouver, BC |
| 9   | Grace Yellow  | 50  | Engineer      | UK            | [email protected]    | 555-3333       | 864 Fir St, Manchester, UK   |
| 10  | Henry Violet  | 32  | Artist        | Australia     | [email protected]    | 555-4444       | 753 Willow St, Melbourne, VIC|
| 11  | Irene Orange  | 26  | Scientist     | New Zealand   | [email protected]    | 555-5555       | 912 Poplar St, Auckland, NZ  |
| 12  | Jack Indigo   | 38  | Teacher       | Ireland       | [email protected]     | 555-6666       | 159 Elm St, Cork, IE         |
| 13  | Karen Red     | 41  | Lawyer        | USA           | [email protected]    | 555-7777       | 357 Cedar St, Boston, MA     |
| 14  | Leo Brown     | 30  | Chef          | Canada        | [email protected]      | 555-8888       | 246 Oak St, Calgary, AB      |
| 15  | Mia Green     | 33  | Musician      | UK            | [email protected]      | 555-9999       | 975 Pine St, Edinburgh, UK   |
| 16  | Noah Yellow   | 29  | Doctor        | Australia     | [email protected]     | 555-0000       | 864 Birch St, Brisbane, QLD  |
| 17  | Olivia Blue   | 35  | Engineer      | New Zealand   | [email protected]   | 555-1212       | 753 Maple St, Hamilton, NZ   |
| 18  | Peter Black   | 42  | Artist        | Ireland       | [email protected]    | 555-3434       | 912 Fir St, Limerick, IE     |
| 19  | Quinn White   | 28  | Scientist     | USA           | [email protected]    | 555-5656       | 159 Willow St, Seattle, WA   |
| 20  | Rachel Red    | 31  | Teacher       | Canada        | [email protected]   | 555-7878       | 357 Poplar St, Ottawa, ON    |
| 21  | Steve Green   | 44  | Lawyer        | UK            | [email protected]    | 555-9090       | 753 Elm St, Birmingham, UK   |
| 22  | Tina Blue     | 36  | Musician      | Australia     | [email protected]     | 555-1213       | 864 Cedar St, Perth, WA      |
| 23  | Umar Black    | 39  | Chef          | New Zealand   | [email protected]     | 555-3435       | 975 Spruce St, Christchurch, NZ|
| 24  | Victor Yellow | 43  | Engineer      | Ireland       | [email protected]   | 555-5657       | 246 Willow St, Galway, IE    |
| 25  | Wendy Orange  | 27  | Artist        | USA           | [email protected]    | 555-7879       | 135 Elm St, Denver, CO       |
| 26  | Xavier Green  | 34  | Scientist     | Canada        | [email protected]   | 555-9091       | 357 Oak St, Montreal, QC     |
| 27  | Yara Red      | 41  | Teacher       | UK            | [email protected]     | 555-1214       | 975 Pine St, Leeds, UK       |
| 28  | Zack Blue     | 30  | Lawyer        | Australia     | [email protected]     | 555-3436       | 135 Birch St, Adelaide, SA   |
| 29  | Amy White     | 33  | Musician      | New Zealand   | [email protected]      | 555-5658       | 159 Maple St, Wellington, NZ |
| 30  | Ben Black     | 38  | Chef          | Ireland       | [email protected]      | 555-7870       | 246 Fir St, Waterford, IE    |
"""
)


def get_generation_time(llm, sampling_params, prompts):
    # time the generation
    start_time = time.time()
    output = llm.generate(prompts, sampling_params=sampling_params)
    end_time = time.time()
    # print the output and generation time
    print("-" * 30)
    print(f"Output: {output[0].outputs[0].text}")
    print(f"Generation time: {end_time - start_time} seconds.")
    print("-" * 30)


def main():
    # set enable_prefix_caching=True to enable APC
    llm = LLM(model="lmsys/longchat-13b-16k", enable_prefix_caching=True)

    sampling_params = SamplingParams(temperature=0, max_tokens=100)

    # Querying the age of John Doe
    get_generation_time(
        llm,
        sampling_params,
        LONG_PROMPT
        + "Question: what is the age of John Doe? Your answer: The age of John Doe is ",
    )

    # Querying the age of Zack Blue
    # This query will be faster since vllm avoids computing the KV cache of LONG_PROMPT again.
    get_generation_time(
        llm,
        sampling_params,
        LONG_PROMPT
        + "Question: what is the age of Zack Blue? Your answer: The age of Zack Blue is ",
    )


if __name__ == "__main__":
    main()