vllm.inputs ¶

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 EmbedsInput(_InputOptions):
    """Represents embeddings-based input to the engine."""

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

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

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

    prompt_token_ids: NotRequired[list[int]]
    """Token IDs of the rendered prompt. Only set for mixed-mode inputs
    (chat completion with `prompt_embeds` content parts). When present,
    `is_token_ids` MUST also be present and have the same length. 
    For pure-embeds inputs this field is absent."""

    is_token_ids: NotRequired[list[bool]]
    """Per-position mask for mixed-mode inputs. `True` means the position
    is a real token ID (use the model's embedding layer); `False` means
    the position uses a pre-computed embedding row from `prompt_embeds`.
    Length MUST equal `len(prompt_token_ids)`.
    For pure-embeds inputs this field is absent."""

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 EncoderDecoderInput(TypedDict):
    """
    A rendered [`EncoderDecoderPrompt`][vllm.inputs.llm.EncoderDecoderPrompt]
    which can be passed to `LLMEngine.add_request` or `AsyncLLM.add_request`.
    """

    type: Literal["enc_dec"]

    encoder_prompt: EncoderInput
    """The inputs for the encoder portion."""

    decoder_prompt: DecoderEngineInput
    """The inputs for the decoder portion."""

    arrival_time: NotRequired[float]
    """The time when the input was received (before rendering)."""

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 MultiModalEncDecInput(MultiModalInput):
    """
    Represents multi-modal input to the engine for encoder-decoder models.

    Note:
        Even text-only encoder-decoder models are currently implemented
        as multi-modal models for convenience.
        (Example: https://github.com/vllm-project/bart-plugin)
    """

    encoder_prompt_token_ids: list[int]
    """The processed token IDs of the encoder prompt."""

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

class MultiModalInput(_InputOptions):
    """Represents multi-modal input to the engine."""

    type: Literal["multimodal"]
    """The type of input."""

    prompt_token_ids: list[int]
    """The processed token IDs which includes placeholder tokens."""

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

    mm_kwargs: "MultiModalKwargsOptionalItems"
    """Keyword arguments to be directly passed to the model after batching."""

    mm_hashes: MultiModalHashes
    """The hashes of the multi-modal data."""

    mm_placeholders: MultiModalPlaceholders
    """
    For each modality, information about the placeholder tokens in
    `prompt_token_ids`.
    """

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

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

class TokensInput(_InputOptions):
    """Represents token-based input to the engine."""

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

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

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

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."""