vllm.entrypoints.serve.disagg.protocol ¶

class GenerateRequest(BaseModel):
    request_id: str = Field(
        default_factory=lambda: f"{random_uuid()}",
        description=(
            "The request_id related to this request. If the caller does "
            "not set it, a random_uuid will be generated. This id is used "
            "through out the inference process and return in response."
        ),
    )
    token_ids: list[int]
    """The token ids to generate text from."""

    @field_validator("token_ids")
    @classmethod
    def validate_token_ids(cls, v: list[int]) -> list[int]:
        if any(t < 0 for t in v):
            raise ValueError("token_ids must not contain negative values")
        return v

    features: MultiModalFeatures | None = None
    """Multimodal hashes and placeholder positions (populated for MM inputs)."""

    sampling_params: SamplingParams
    """The sampling parameters for the model."""

    model: str | None = None

    stream: bool | None = False
    stream_options: StreamOptions | None = None
    cache_salt: str | None = Field(
        default=None,
        description=(
            "If specified, the prefix cache will be salted with the provided "
            "string to prevent an attacker to guess prompts in multi-user "
            "environments. The salt should be random, protected from "
            "access by 3rd parties, and long enough to be "
            "unpredictable (e.g., 43 characters base64-encoded, corresponding "
            "to 256 bit)."
        ),
    )
    priority: int = Field(
        default=0,
        ge=-(2**63),
        le=2**63 - 1,
        description=(
            "The priority of the request (lower means earlier handling; "
            "default: 0). Any priority other than 0 will raise an error "
            "if the served model does not use priority scheduling."
        ),
    )
    kv_transfer_params: dict[str, Any] | None = Field(
        default=None,
        description="KVTransfer parameters used for disaggregated serving.",
    )

    def build_tok_params(self, model_config: ModelConfig) -> TokenizeParams:
        return TokenizeParams(
            max_total_tokens=None,
            max_output_tokens=0,
        )

class MultiModalFeatures(BaseModel):
    """Lightweight multimodal metadata produced by the render step.

    Carries hashes (for cache lookup / identification) and placeholder
    positions so the downstream ``/generate`` service knows *where* in
    the token sequence each multimodal item lives.

    .. note:: Phase 1 — metadata only.
       Phase 2 should add ``mm_kwargs`` (processed tensor data) using a
       binary transport so the ``/generate`` side can skip re-processing.
       The ``/generate`` endpoint must also be updated to inject these
       features into ``ProcessorInputs`` before passing to
       ``InputProcessor.process_inputs``.
    """

    mm_hashes: dict[str, list[str]]
    """Per-modality item hashes, e.g. ``{"image": ["abc", "def"]}``."""

    mm_placeholders: dict[str, list[PlaceholderRangeInfo]]
    """Per-modality placeholder ranges in the token sequence."""

class PlaceholderRangeInfo(BaseModel):
    """Serializable placeholder location for a single multi-modal item."""

    offset: int
    """Start index of the placeholder tokens in the prompt."""

    length: int
    """Number of placeholder tokens."""