vllm.inputs.data ¶

class DataPrompt(_PromptOptions):
    """
    Represents generic inputs that are converted to
    [`PromptType`][vllm.inputs.data.PromptType] by IO processor plugins.
    """

    data: Any
    """The input data."""

    data_format: str
    """The input data format."""

class EmbedsInputs(_InputOptions):
    """Represents embeddings-based inputs."""

    type: Literal["embeds"]
    """The type of inputs."""

    prompt_embeds: torch.Tensor
    """The embeddings of the prompt."""

class EmbedsPrompt(_PromptOptions):
    """Schema for a prompt provided via token embeddings."""

    prompt_embeds: torch.Tensor
    """The embeddings of the prompt."""

    prompt: NotRequired[str]
    """The prompt text corresponding to the token embeddings, if available."""

class EncoderDecoderInputs(TypedDict):
    """
    A processed pair of encoder and decoder singleton prompts.
    [`InputPreprocessor`][vllm.inputs.preprocess.InputPreprocessor]
    which can be passed to
    [`InputProcessor`][vllm.v1.engine.input_processor.InputProcessor]
    for encoder-decoder models.
    """

    encoder: EncoderInputs
    """The inputs for the encoder portion."""

    decoder: DecoderInputs
    """The inputs for the decoder portion."""

class ExplicitEncoderDecoderPrompt(TypedDict):
    """
    Schema for a pair of encoder and decoder singleton prompts.

    Note:
        This schema is not valid for decoder-only models.
    """

    encoder_prompt: EncoderPrompt
    """The prompt for the encoder part of the model."""

    decoder_prompt: DecoderPrompt | None
    """
    The prompt for the decoder part of the model.

    Passing `None` will cause the prompt to be inferred automatically.
    """

@dataclass
class StreamingInput:
    """Input data for a streaming generation request.

    This is used with generate() to support multi-turn streaming sessions
    where inputs are provided via an async generator.
    """

    prompt: PromptType
    sampling_params: SamplingParams | None = None

class TextPrompt(_PromptOptions):
    """Schema for a text prompt."""

    prompt: str
    """The input text to be tokenized before passing to the model."""

class TokenInputs(_InputOptions):
    """Represents token-based inputs."""

    type: Literal["token"]
    """The type of inputs."""

    prompt_token_ids: list[int]
    """The token IDs of the prompt."""

class TokensPrompt(_PromptOptions):
    """Schema for a tokenized prompt."""

    prompt_token_ids: list[int]
    """A list of token IDs to pass to the model."""

    prompt: NotRequired[str]
    """The prompt text corresponding to the token IDs, if available."""

    token_type_ids: NotRequired[list[int]]
    """A list of token type IDs to pass to the cross encoder model."""

class _InputOptions(TypedDict):
    """
    Additional options available to all input types.
    """

    cache_salt: NotRequired[str]
    """Optional cache salt to be used for prefix caching."""

class _PromptOptions(TypedDict):
    """
    Additional options available to all
    [`SingletonPrompt`][vllm.inputs.data.SingletonPrompt].
    """

    multi_modal_data: NotRequired[MultiModalDataDict | None]
    """
    Optional multi-modal data to pass to the model,
    if the model supports it.
    """

    mm_processor_kwargs: NotRequired[dict[str, Any] | None]
    """
    Optional multi-modal processor kwargs to be forwarded to the
    multimodal input mapper & processor. Note that if multiple modalities
    have registered mappers etc for the model being considered, we attempt
    to pass the mm_processor_kwargs to each of them.
    """

    multi_modal_uuids: NotRequired[MultiModalUUIDDict]
    """
    Optional user-specified UUIDs for multimodal items, mapped by modality.
    Lists must match the number of items per modality and may contain `None`.
    For `None` entries, the hasher will compute IDs automatically; non-None
    entries override the default hashes for caching, and MUST be unique per
    multimodal item.
    """

    cache_salt: NotRequired[str]
    """
    Optional cache salt to be used for prefix caching.
    """