Skip to content

vLLM

vLLM

Bases: LLM, CudaDevicePlacementMixin

vLLM library LLM implementation.

Attributes:

Name Type Description
model str

the model Hugging Face Hub repo id or a path to a directory containing the model weights and configuration files.
model_kwargs Optional[RuntimeParameter[Dict[str, Any]]]

additional dictionary of keyword arguments that will be passed to the LLM class of vllm library.
chat_template Optional[str]

a chat template that will be used to build the prompts before sending them to the model. If not provided, the chat template defined in the tokenizer config will be used. If not provided and the tokenizer doesn't have a chat template, then ChatML template will be used. Defaults to None.
_model Optional[LLM]

the vLLM model instance. This attribute is meant to be used internally and should not be accessed directly. It will be set in the load method.
_tokenizer Optional[PreTrainedTokenizer]

the tokenizer instance used to format the prompt before passing it to the LLM. This attribute is meant to be used internally and should not be accessed directly. It will be set in the load method.
Runtime parameters
  • model_kwargs: additional dictionary of keyword arguments that will be passed to the LLM class of vllm library.
Source code in src/distilabel/llms/vllm.py 
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
class vLLM(LLM, CudaDevicePlacementMixin):
    """`vLLM` library LLM implementation.

    Attributes:
        model: the model Hugging Face Hub repo id or a path to a directory containing the
            model weights and configuration files.
        model_kwargs: additional dictionary of keyword arguments that will be passed to
            the `LLM` class of `vllm` library.
        chat_template: a chat template that will be used to build the prompts before
            sending them to the model. If not provided, the chat template defined in the
            tokenizer config will be used. If not provided and the tokenizer doesn't have
            a chat template, then ChatML template will be used. Defaults to `None`.
        _model: the `vLLM` model instance. This attribute is meant to be used internally
            and should not be accessed directly. It will be set in the `load` method.
        _tokenizer: the tokenizer instance used to format the prompt before passing it to
            the `LLM`. This attribute is meant to be used internally and should not be
            accessed directly. It will be set in the `load` method.

    Runtime parameters:
        - `model_kwargs`: additional dictionary of keyword arguments that will be passed to
            the `LLM` class of `vllm` library.
    """

    model: str
    model_kwargs: Optional[RuntimeParameter[Dict[str, Any]]] = Field(
        default_factory=dict,
        description="Additional dictionary of keyword arguments that will be passed to the"
        " `LLM` class of `vllm` library.",
    )
    chat_template: Optional[str] = None

    _model: Optional["_vLLM"] = PrivateAttr(...)
    _tokenizer: Optional["PreTrainedTokenizer"] = PrivateAttr(...)

    def load(self) -> None:
        """Loads the `vLLM` model using either the path or the Hugging Face Hub repository id.
        Additionally, this method also sets the `chat_template` for the tokenizer, so as to properly
        parse the list of OpenAI formatted inputs using the expected format by the model, otherwise, the
        default value is ChatML format, unless explicitly provided.
        """
        super().load()

        CudaDevicePlacementMixin.load(self)

        try:
            from vllm import LLM as _vLLM
            from vllm import SamplingParams as _SamplingParams

            global SamplingParams
            SamplingParams = _SamplingParams
        except ImportError as ie:
            raise ImportError(
                "vLLM is not installed. Please install it using `pip install vllm`."
            ) from ie

        self._model = _vLLM(self.model, **self.model_kwargs)  # type: ignore
        self._tokenizer = self._model.get_tokenizer()  # type: ignore

        if self.chat_template is not None:
            self._tokenizer.chat_template = self.chat_template  # type: ignore
        elif (
            self._tokenizer.chat_template is None  # type: ignore
            and self._tokenizer.default_chat_template is None  # type: ignore
        ):
            self._tokenizer.chat_template = CHATML_TEMPLATE

    @property
    def model_name(self) -> str:
        """Returns the model name used for the LLM."""
        return self.model

    def prepare_input(self, input: "ChatType") -> str:
        """Prepares the input by applying the chat template to the input, which is formatted
        as an OpenAI conversation, and adding the generation prompt.
        """
        return self._tokenizer.apply_chat_template(  # type: ignore
            input,  # type: ignore
            tokenize=False,
            add_generation_prompt=True,  # type: ignore
        )

    @validate_call
    def generate(  # type: ignore
        self,
        inputs: List[ChatType],
        num_generations: int = 1,
        max_new_tokens: int = 128,
        frequency_penalty: float = 0.0,
        presence_penalty: float = 0.0,
        temperature: float = 1.0,
        top_p: float = 1.0,
        top_k: int = -1,
        extra_sampling_params: Optional[Dict[str, Any]] = None,
    ) -> List[GenerateOutput]:
        """Generates `num_generations` responses for each input using the text generation
        pipeline.

        Args:
            inputs: a list of inputs in chat format to generate responses for.
            num_generations: the number of generations to create per input. Defaults to
                `1`.
            max_new_tokens: the maximum number of new tokens that the model will generate.
                Defaults to `128`.
            frequency_penalty: the repetition penalty to use for the generation. Defaults
                to `0.0`.
            presence_penalty: the presence penalty to use for the generation. Defaults to
                `0.0`.
            temperature: the temperature to use for the generation. Defaults to `0.1`.
            top_p: the top-p value to use for the generation. Defaults to `1.0`.
            top_k: the top-k value to use for the generation. Defaults to `0`.
            extra_sampling_params: dictionary with additional arguments to be passed to
                the `SamplingParams` class from `vllm`.

        Returns:
            A list of lists of strings containing the generated responses for each input.
        """
        if extra_sampling_params is None:
            extra_sampling_params = {}

        sampling_params = SamplingParams(  # type: ignore
            n=num_generations,
            presence_penalty=presence_penalty,
            frequency_penalty=frequency_penalty,
            temperature=temperature,
            top_p=top_p,
            top_k=top_k,
            max_tokens=max_new_tokens,
            **extra_sampling_params,
        )

        prepared_inputs = [self.prepare_input(input) for input in inputs]
        batch_outputs = self._model.generate(  # type: ignore
            prepared_inputs,
            sampling_params,
            use_tqdm=False,  # type: ignore
        )
        return [
            [output.text for output in outputs.outputs] for outputs in batch_outputs
        ]

model_name: str property

Returns the model name used for the LLM.

generate(inputs, num_generations=1, max_new_tokens=128, frequency_penalty=0.0, presence_penalty=0.0, temperature=1.0, top_p=1.0, top_k=-1, extra_sampling_params=None)

Generates num_generations responses for each input using the text generation pipeline.

Parameters:

Name Type Description Default
inputs List[ChatType]

a list of inputs in chat format to generate responses for.

 required
num_generations int

the number of generations to create per input. Defaults to 1.

 1
max_new_tokens int

the maximum number of new tokens that the model will generate. Defaults to 128.

 128
frequency_penalty float

the repetition penalty to use for the generation. Defaults to 0.0.

 0.0
presence_penalty float

the presence penalty to use for the generation. Defaults to 0.0.

 0.0
temperature float

the temperature to use for the generation. Defaults to 0.1.

 1.0
top_p float

the top-p value to use for the generation. Defaults to 1.0.

 1.0
top_k int

the top-k value to use for the generation. Defaults to 0.

 -1
extra_sampling_params Optional[Dict[str, Any]]

dictionary with additional arguments to be passed to the SamplingParams class from vllm.

 None

Returns:

Type Description
List[GenerateOutput]

A list of lists of strings containing the generated responses for each input.
Source code in src/distilabel/llms/vllm.py 
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
@validate_call
def generate(  # type: ignore
    self,
    inputs: List[ChatType],
    num_generations: int = 1,
    max_new_tokens: int = 128,
    frequency_penalty: float = 0.0,
    presence_penalty: float = 0.0,
    temperature: float = 1.0,
    top_p: float = 1.0,
    top_k: int = -1,
    extra_sampling_params: Optional[Dict[str, Any]] = None,
) -> List[GenerateOutput]:
    """Generates `num_generations` responses for each input using the text generation
    pipeline.

    Args:
        inputs: a list of inputs in chat format to generate responses for.
        num_generations: the number of generations to create per input. Defaults to
            `1`.
        max_new_tokens: the maximum number of new tokens that the model will generate.
            Defaults to `128`.
        frequency_penalty: the repetition penalty to use for the generation. Defaults
            to `0.0`.
        presence_penalty: the presence penalty to use for the generation. Defaults to
            `0.0`.
        temperature: the temperature to use for the generation. Defaults to `0.1`.
        top_p: the top-p value to use for the generation. Defaults to `1.0`.
        top_k: the top-k value to use for the generation. Defaults to `0`.
        extra_sampling_params: dictionary with additional arguments to be passed to
            the `SamplingParams` class from `vllm`.

    Returns:
        A list of lists of strings containing the generated responses for each input.
    """
    if extra_sampling_params is None:
        extra_sampling_params = {}

    sampling_params = SamplingParams(  # type: ignore
        n=num_generations,
        presence_penalty=presence_penalty,
        frequency_penalty=frequency_penalty,
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        max_tokens=max_new_tokens,
        **extra_sampling_params,
    )

    prepared_inputs = [self.prepare_input(input) for input in inputs]
    batch_outputs = self._model.generate(  # type: ignore
        prepared_inputs,
        sampling_params,
        use_tqdm=False,  # type: ignore
    )
    return [
        [output.text for output in outputs.outputs] for outputs in batch_outputs
    ]

load()

Loads the vLLM model using either the path or the Hugging Face Hub repository id. Additionally, this method also sets the chat_template for the tokenizer, so as to properly parse the list of OpenAI formatted inputs using the expected format by the model, otherwise, the default value is ChatML format, unless explicitly provided.

Source code in src/distilabel/llms/vllm.py 
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
def load(self) -> None:
    """Loads the `vLLM` model using either the path or the Hugging Face Hub repository id.
    Additionally, this method also sets the `chat_template` for the tokenizer, so as to properly
    parse the list of OpenAI formatted inputs using the expected format by the model, otherwise, the
    default value is ChatML format, unless explicitly provided.
    """
    super().load()

    CudaDevicePlacementMixin.load(self)

    try:
        from vllm import LLM as _vLLM
        from vllm import SamplingParams as _SamplingParams

        global SamplingParams
        SamplingParams = _SamplingParams
    except ImportError as ie:
        raise ImportError(
            "vLLM is not installed. Please install it using `pip install vllm`."
        ) from ie

    self._model = _vLLM(self.model, **self.model_kwargs)  # type: ignore
    self._tokenizer = self._model.get_tokenizer()  # type: ignore

    if self.chat_template is not None:
        self._tokenizer.chat_template = self.chat_template  # type: ignore
    elif (
        self._tokenizer.chat_template is None  # type: ignore
        and self._tokenizer.default_chat_template is None  # type: ignore
    ):
        self._tokenizer.chat_template = CHATML_TEMPLATE

prepare_input(input)

Prepares the input by applying the chat template to the input, which is formatted as an OpenAI conversation, and adding the generation prompt.

Source code in src/distilabel/llms/vllm.py 
105
106
107
108
109
110
111
112
113
def prepare_input(self, input: "ChatType") -> str:
    """Prepares the input by applying the chat template to the input, which is formatted
    as an OpenAI conversation, and adding the generation prompt.
    """
    return self._tokenizer.apply_chat_template(  # type: ignore
        input,  # type: ignore
        tokenize=False,
        add_generation_prompt=True,  # type: ignore
    )