基礎

基礎#

LLM 類提供了用於執行離線推理的主要 Python 介面，即在不使用單獨的模型推理伺服器的情況下與模型進行互動。

用法#

此示例中的第一個指令碼展示了 vLLM 最基本的使用方法。如果您是 Python 和 vLLM 的新手，您應該從這裡開始。

python examples/offline_inference/basic/basic.py

其餘指令碼包含一個引數解析器，您可以使用它傳遞任何與 LLM 相容的引數。嘗試使用 --help 執行指令碼以獲取所有可用引數的列表。

python examples/offline_inference/basic/classify.py

python examples/offline_inference/basic/embed.py

python examples/offline_inference/basic/score.py

聊天和生成指令碼也接受取樣引數：max_tokens、temperature、top_p 和 top_k。

python examples/offline_inference/basic/chat.py

python examples/offline_inference/basic/generate.py

特性#

在支援傳遞引數的指令碼中，您可以嘗試以下特性。

預設生成配置#

--generation-config 引數指定在呼叫 LLM.get_default_sampling_params() 時從哪裡載入生成配置。如果設定為 'auto'，則將從模型路徑載入生成配置。如果設定為資料夾路徑，則將從指定的資料夾路徑載入生成配置。如果未提供，則將使用 vLLM 預設設定。

如果在生成配置中指定了 max_new_tokens，則它會為所有請求設定伺服器範圍的輸出令牌數量限制。

使用以下引數親自嘗試一下

--generation-config auto

量化#

AQLM#

vLLM 支援使用 AQLM 量化的模型。

透過將以下模型之一傳遞給 --model 引數親自嘗試一下

ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf
ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf
ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf
ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf
BlackSamorez/TinyLlama-1_1B-Chat-v1_0-AQLM-2Bit-1x16-hf

其中一些模型可能對於單個 GPU 來說太大。您可以透過將 --tensor-parallel-size 設定為所需 GPU 的數量，將它們拆分到多個 GPU 上。

GGUF#

vLLM 支援使用 GGUF 量化的模型。

透過下載 GUFF 量化模型並使用以下引數親自嘗試一下

from huggingface_hub import hf_hub_download
repo_id = "bartowski/Phi-3-medium-4k-instruct-GGUF"
filename = "Phi-3-medium-4k-instruct-IQ2_M.gguf"
print(hf_hub_download(repo_id, filename=filename))

--model {local-path-printed-above} --tokenizer microsoft/Phi-3-medium-4k-instruct

CPU 解除安裝#

--cpu-offload-gb 引數可以被視為增加 GPU 記憶體大小的虛擬方法。例如，如果您有一個 24 GB 的 GPU 並將其設定為 10，實際上您可以將其視為 34 GB 的 GPU。然後，您可以載入具有 BF16 權重的 13B 模型，這至少需要 26GB 的 GPU 記憶體。請注意，這需要快速的 CPU-GPU 互連，因為模型的一部分在每個模型前向傳遞中都會從 CPU 記憶體動態載入到 GPU 記憶體。

使用以下引數親自嘗試一下

--model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10

示例材料#

basic.py

# SPDX-License-Identifier: Apache-2.0

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="facebook/opt-125m")
# 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.
print("\nGenerated Outputs:\n" + "-" * 60)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt:    {prompt!r}")
    print(f"Output:    {generated_text!r}")
    print("-" * 60)

chat.py

# SPDX-License-Identifier: Apache-2.0

from vllm import LLM, EngineArgs
from vllm.utils import FlexibleArgumentParser


def main(args: dict):
    # Pop arguments not used by LLM
    max_tokens = args.pop("max_tokens")
    temperature = args.pop("temperature")
    top_p = args.pop("top_p")
    top_k = args.pop("top_k")
    chat_template_path = args.pop("chat_template_path")

    # Create an LLM
    llm = LLM(**args)

    # Create sampling params object
    sampling_params = llm.get_default_sampling_params()
    if max_tokens is not None:
        sampling_params.max_tokens = max_tokens
    if temperature is not None:
        sampling_params.temperature = temperature
    if top_p is not None:
        sampling_params.top_p = top_p
    if top_k is not None:
        sampling_params.top_k = top_k

    def print_outputs(outputs):
        print("\nGenerated Outputs:\n" + "-" * 80)
        for output in outputs:
            prompt = output.prompt
            generated_text = output.outputs[0].text
            print(f"Prompt: {prompt!r}\n")
            print(f"Generated text: {generated_text!r}")
            print("-" * 80)

    print("=" * 80)

    # In this script, we demonstrate how to pass input to the chat method:
    conversation = [
        {
            "role": "system",
            "content": "You are a helpful assistant"
        },
        {
            "role": "user",
            "content": "Hello"
        },
        {
            "role": "assistant",
            "content": "Hello! How can I assist you today?"
        },
        {
            "role": "user",
            "content":
            "Write an essay about the importance of higher education.",
        },
    ]
    outputs = llm.chat(conversation, sampling_params, use_tqdm=False)
    print_outputs(outputs)

    # You can run batch inference with llm.chat API
    conversations = [conversation for _ in range(10)]

    # We turn on tqdm progress bar to verify it's indeed running batch inference
    outputs = llm.chat(conversations, sampling_params, use_tqdm=True)
    print_outputs(outputs)

    # A chat template can be optionally supplied.
    # If not, the model will use its default chat template.
    if chat_template_path is not None:
        with open(chat_template_path) as f:
            chat_template = f.read()

        outputs = llm.chat(
            conversations,
            sampling_params,
            use_tqdm=False,
            chat_template=chat_template,
        )


if __name__ == "__main__":
    parser = FlexibleArgumentParser()
    # Add engine args
    engine_group = parser.add_argument_group("Engine arguments")
    EngineArgs.add_cli_args(engine_group)
    engine_group.set_defaults(model="meta-llama/Llama-3.2-1B-Instruct")
    # Add sampling params
    sampling_group = parser.add_argument_group("Sampling parameters")
    sampling_group.add_argument("--max-tokens", type=int)
    sampling_group.add_argument("--temperature", type=float)
    sampling_group.add_argument("--top-p", type=float)
    sampling_group.add_argument("--top-k", type=int)
    # Add example params
    parser.add_argument("--chat-template-path", type=str)
    args: dict = vars(parser.parse_args())
    main(args)

classify.py

# SPDX-License-Identifier: Apache-2.0

from argparse import Namespace

from vllm import LLM, EngineArgs
from vllm.utils import FlexibleArgumentParser


def main(args: Namespace):
    # 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 an LLM.
    # You should pass task="classify" for classification models
    model = LLM(**vars(args))

    # Generate logits. The output is a list of ClassificationRequestOutputs.
    outputs = model.classify(prompts)

    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for prompt, output in zip(prompts, outputs):
        probs = output.outputs.probs
        probs_trimmed = ((str(probs[:16])[:-1] +
                          ", ...]") if len(probs) > 16 else probs)
        print(f"Prompt: {prompt!r} \n"
              f"Class Probabilities: {probs_trimmed} (size={len(probs)})")
        print("-" * 60)


if __name__ == "__main__":
    parser = FlexibleArgumentParser()
    parser = EngineArgs.add_cli_args(parser)
    # Set example specific arguments
    parser.set_defaults(model="jason9693/Qwen2.5-1.5B-apeach",
                        task="classify",
                        enforce_eager=True)
    args = parser.parse_args()
    main(args)

embed.py

# SPDX-License-Identifier: Apache-2.0

from argparse import Namespace

from vllm import LLM, EngineArgs
from vllm.utils import FlexibleArgumentParser


def main(args: Namespace):
    # 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 an LLM.
    # You should pass task="embed" for embedding models
    model = LLM(**vars(args))

    # Generate embedding. The output is a list of EmbeddingRequestOutputs.
    outputs = model.embed(prompts)

    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for prompt, output in zip(prompts, outputs):
        embeds = output.outputs.embedding
        embeds_trimmed = ((str(embeds[:16])[:-1] +
                           ", ...]") if len(embeds) > 16 else embeds)
        print(f"Prompt: {prompt!r} \n"
              f"Embeddings: {embeds_trimmed} (size={len(embeds)})")
        print("-" * 60)


if __name__ == "__main__":
    parser = FlexibleArgumentParser()
    parser = EngineArgs.add_cli_args(parser)
    # Set example specific arguments
    parser.set_defaults(model="intfloat/e5-mistral-7b-instruct",
                        task="embed",
                        enforce_eager=True)
    args = parser.parse_args()
    main(args)

generate.py

# SPDX-License-Identifier: Apache-2.0

from vllm import LLM, EngineArgs
from vllm.utils import FlexibleArgumentParser


def main(args: dict):
    # Pop arguments not used by LLM
    max_tokens = args.pop("max_tokens")
    temperature = args.pop("temperature")
    top_p = args.pop("top_p")
    top_k = args.pop("top_k")

    # Create an LLM
    llm = LLM(**args)

    # Create a sampling params object
    sampling_params = llm.get_default_sampling_params()
    if max_tokens is not None:
        sampling_params.max_tokens = max_tokens
    if temperature is not None:
        sampling_params.temperature = temperature
    if top_p is not None:
        sampling_params.top_p = top_p
    if top_k is not None:
        sampling_params.top_k = top_k

    # Generate texts from the prompts. The output is a list of RequestOutput
    # objects that contain the prompt, generated text, and other information.
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]
    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}")


if __name__ == "__main__":
    parser = FlexibleArgumentParser()
    # Add engine args
    engine_group = parser.add_argument_group("Engine arguments")
    EngineArgs.add_cli_args(engine_group)
    engine_group.set_defaults(model="meta-llama/Llama-3.2-1B-Instruct")
    # Add sampling params
    sampling_group = parser.add_argument_group("Sampling parameters")
    sampling_group.add_argument("--max-tokens", type=int)
    sampling_group.add_argument("--temperature", type=float)
    sampling_group.add_argument("--top-p", type=float)
    sampling_group.add_argument("--top-k", type=int)
    args: dict = vars(parser.parse_args())
    main(args)

score.py

# SPDX-License-Identifier: Apache-2.0

from argparse import Namespace

from vllm import LLM, EngineArgs
from vllm.utils import FlexibleArgumentParser


def main(args: Namespace):
    # Sample prompts.
    text_1 = "What is the capital of France?"
    texts_2 = [
        "The capital of Brazil is Brasilia.",
        "The capital of France is Paris.",
    ]

    # Create an LLM.
    # You should pass task="score" for cross-encoder models
    model = LLM(**vars(args))

    # Generate scores. The output is a list of ScoringRequestOutputs.
    outputs = model.score(text_1, texts_2)

    # Print the outputs.
    print("\nGenerated Outputs:\n" + "-" * 60)
    for text_2, output in zip(texts_2, outputs):
        score = output.outputs.score
        print(f"Pair: {[text_1, text_2]!r} \nScore: {score}")
        print("-" * 60)


if __name__ == "__main__":
    parser = FlexibleArgumentParser()
    parser = EngineArgs.add_cli_args(parser)
    # Set example specific arguments
    parser.set_defaults(model="BAAI/bge-reranker-v2-m3",
                        task="score",
                        enforce_eager=True)
    args = parser.parse_args()
    main(args)

基礎

目錄

基礎#

用法#

特性#

預設生成配置#

量化#

AQLM#

GGUF#

CPU 解除安裝#

示例材料#