vllm.inputs.llm ¶

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

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

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

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."""

    prompt_token_ids: NotRequired[list[int]]
    """Token IDs for mixed-mode inputs (chat completion with
    `prompt_embeds` content parts). The tokens at positions where 
    `prompt_is_token_ids` is `False` are placeholder tokens that 
    get replaced by entries from `prompt_embeds` in the forward pass."""

    prompt_is_token_ids: NotRequired[list[bool]]
    """Per-position mask, `True` uses the real token ID, `False` uses
    the corresponding entry from `prompt_embeds`. 
    Must be the same length as `prompt_token_ids` when both are set."""

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.
    """

@final
class MultiModalDataBuiltins(TypedDict, total=False):
    """Type annotations for modality types predefined by vLLM."""

    image: ModalityData["ImageItem"]
    """The input image(s)."""

    video: ModalityData["VideoItem"]
    """The input video(s)."""

    audio: ModalityData["AudioItem"]
    """The input audio(s)."""

    vision_chunk: ModalityData["VisionChunk"]
    """The input visual atom(s) - unified modality for images and video chunks."""

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

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

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

    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.
    """