vllm_omni.model_executor.models.output_templates ¶

Bases: NamedTuple

Output from the merged Omni model containing both text and audio.

intermediate_tensors: IntermediateTensors | None = None

multimodal_outputs: OmniPayload | None = None

next_token_id: Tensor | None = None

text_hidden_states: Tensor

Bases: NamedTuple

A batch tensor whose producer transfers ownership to the buffer.

The producer must have freshly allocated the tensor (e.g. an index_select result) and must not write it afterwards. The buffer keeps row views instead of taking a second snapshot. Tensors without this marker are treated as borrowed (graph output / shared scratch) and still get a clone.

tensor: Tensor