Skip to content

`vllm.entrypoints.serve.engine.protocol` ¶

Classes:

PromptTokenUsageInfo –

`PromptTokenUsageInfo` ¶

Bases: OpenAIBaseModel

Attributes:

multimodal_tokens (dict[str, int] | None) –

Prompt tokens contributed by each input modality, keyed by modality name

Source code in vllm/entrypoints/serve/engine/protocol.py

class PromptTokenUsageInfo(OpenAIBaseModel):
    cached_tokens: int | None = None
    created_cache_tokens: int | None = None
    multimodal_tokens: dict[str, int] | None = None
    """Prompt tokens contributed by each input modality, keyed by modality name
    (e.g. `image`, `audio`, `video`). A breakdown of the multimodal
    placeholder tokens already counted in `prompt_tokens`; `None` when the
    request has no multimodal input."""

`multimodal_tokens = None` `class-attribute` `instance-attribute` ¶

Prompt tokens contributed by each input modality, keyed by modality name (e.g. image, audio, video). A breakdown of the multimodal placeholder tokens already counted in prompt_tokens; None when the request has no multimodal input.