Skip to content

vllm_omni.diffusion.request ¶

DUMMY_DIFFUSION_REQUEST_ID `module-attribute` ¶

DUMMY_DIFFUSION_REQUEST_ID = 'dummy_req_id'

OmniDiffusionRequest `dataclass` ¶

Input payload for a single diffusion request.

This dataclass contains the prompt and sampling parameters for the diffusion pipeline execution. It also contains a request_id for other components to trace this request and its outputs. The runner wraps one or more requests into a DiffusionRequestBatch before pipeline execution.

kv_sender_info `class-attribute` `instance-attribute` ¶

kv_sender_info: dict | None = None

prompt `instance-attribute` ¶

prompt: OmniPromptType

request_id `instance-attribute` ¶

request_id: str

sampling_params `instance-attribute` ¶

sampling_params: OmniDiffusionSamplingParams

is_dummy_run ¶

is_dummy_run() -> bool

is_dummy_run_request_id `classmethod` ¶

is_dummy_run_request_id(request_id: str | None) -> bool