vllm_omni.diffusion.worker.utils ¶

Bases: ABC

get_request_output(request_id: str) -> RunnerOutput | None

Bases: BaseRunnerOutput

request_ids: list[str]

runner_outputs: list[RunnerOutput]

from_list(
    runner_output_list: list[RunnerOutput],
) -> BatchRunnerOutput

get_request_output(request_id: str) -> RunnerOutput | None

Per-request mutable state across all pipeline stages.

Owned by Runner and passed through all step-execution stages: prepare_encode() initializes/updates fields, denoise_step() and step_scheduler() mutate per-step fields, and post_decode() consumes final latents. This state object is also the cache unit for future continuous batching.

This dataclass keeps only the minimal cross-model state required by the step-execution contract. Pipeline-specific state should be stored in extra and promoted here only when it becomes shared across models.

Examples:

• Wan-style pipelines may keep condition, first_frame_mask, or image_embeds in extra.
• Bagel-style pipelines may keep gen_context, cfg_text_context, cfg_img_context, or image_shape in extra.

current_timestep: Tensor | None

denoise_completed: bool

do_true_cfg: bool = False

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

guidance: Tensor | None = None

img_shapes: list | None = None

latents: Tensor | None = None

negative_prompt_embeds: Tensor | None = None

negative_prompt_embeds_mask: Tensor | None = None

negative_txt_seq_lens: list[int] | None = None

new_request: bool

prompt_embeds: Tensor | None = None

prompt_embeds_mask: Tensor | None = None

prompts: list[OmniPromptType] | None = None

request_id: str

sampling: OmniDiffusionSamplingParams

scheduler: Any | None = None

step_index: int = 0

timesteps: Tensor | list[Tensor] | None = None

total_steps: int

txt_seq_lens: list[int] | None = None

Bases: BaseRunnerOutput

Output of a single denoising step for a request.

NOTE: latents may be None when returned through IPC to avoid serialization overhead. The actual latents are kept in Worker's _request_state_cache.

finished: bool = False

request_id: str

result: DiffusionOutput | None = None

step_index: int | None = None

get_request_output(request_id: str) -> RunnerOutput | None