vllm_omni.engine.mm_outputs ¶

Multimodal output data structures for vLLM-Omni.

This module defines structured types for multimodal outputs.

MultimodalCompletionOutput `dataclass` ¶

Bases: CompletionOutput

CompletionOutput with multimodal support.

Inherits all CompletionOutput fields and adds multimodal_output. As a CompletionOutput subclass, compatible with all existing vLLM consumers.

multimodal_output = multimodal_output

Structured multimodal output payload.

Attributes:

Name	Type	Description
`tensors`	`dict[str, Tensor]`	Dictionary mapping modality/key names to their tensors.
`metadata`	`dict[str, Any]`	Optional dictionary for non-tensor metadata (e.g., sample rate for audio, image dimensions).

is_empty: bool

Return True if the payload has no tensors.

metadata: dict[str, Any] = field(default_factory=dict)

primary_tensor: Tensor | None

Return the first tensor in the payload, or None if empty.

tensors: dict[str, Tensor] = field(default_factory=dict)

from_dict(
    data: dict[str, Any] | None,
) -> MultimodalPayload | None

Create a MultimodalPayload from a raw dictionary.

Separates torch.Tensor values into tensors and everything else into metadata.

get(key: str) -> Tensor | None

Get a tensor by key, returning None if not found.