Modules:
| Name | Description |
|---|---|
base_scheduler | |
interface | |
request_scheduler | |
step_scheduler | |
dataclass ¶
Cached diffusion requests that only need their request ids resent.
dataclass ¶
Scheduler-owned state for one queued OmniDiffusionRequest.
class-attribute instance-attribute ¶
sampling_params_key: SamplingParamsKey | None = None
dataclass ¶
Output of a single scheduling cycle.
cached property ¶
All scheduled request ids in this cycle, including both new and cached ones.
dataclass ¶
Full request payload for a newly scheduled diffusion request.
Bases: _BaseScheduler
Diffusion scheduler with vLLM-style waiting/running queues.
update_from_output(
sched_output: DiffusionSchedulerOutput,
output: RunnerOutput,
) -> set[str]
Bases: ABC
Abstract lifecycle contract for diffusion schedulers.
abstractmethod ¶
add_request(request: OmniDiffusionRequest) -> str
Add a request and return the scheduler-owned request id.
abstractmethod ¶
finish_requests(
request_ids: str | list[str],
status: DiffusionRequestStatus,
) -> None
Mark one or more requests finished.
abstractmethod ¶
get_request_state(
request_id: str,
) -> DiffusionRequestState | None
Return request state if present.
abstractmethod ¶
has_requests() -> bool
Return whether the scheduler still owns runnable requests.
abstractmethod ¶
initialize(od_config: OmniDiffusionConfig) -> None
Initialize or reset scheduler state.
abstractmethod ¶
pop_request_state(
request_id: str,
) -> DiffusionRequestState | None
Remove and return request state if present.
abstractmethod ¶
Preempt a running request back to waiting.
abstractmethod ¶
update_from_output(
sched_output: DiffusionSchedulerOutput,
output: RunnerOutput,
) -> set[str]
Update scheduler state from executor output.
Bases: _BaseScheduler
Placeholder scheduler that advances a request one denoise step per update.
update_from_output(
sched_output: DiffusionSchedulerOutput,
output: RunnerOutput,
) -> set[str]