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 | RequestBatchSamplingParamsKey | None
) = None
class-attribute instance-attribute ¶
status: DiffusionRequestStatus = (
DiffusionRequestStatus.WAITING
)
dataclass ¶
Output of a single scheduling cycle.
cached property ¶
All scheduled request ids in this cycle, including both new and cached ones.
dataclass ¶
Payload for a newly scheduled diffusion request.
Carries the already-initialized request object so executors and workers do not re-run OmniDiffusionRequest.__post_init__ and mutate sentinel-based fields like guidance_scale_provided.
dataclass ¶
Request level Batch-compatibility key derived from OmniDiffusionSamplingParams.
Only request-batch-wide fields belong here. Request-local values such as seeds, generators, latent tensors, timesteps, and pipeline-specific extra_args are read per request from DiffusionRequestBatch.sampling_params_list.
dataclass ¶
Denoise step level Batch-compatibility key derived from OmniDiffusionSamplingParams.
Only requests with the same key can be batched together. Fields not included here are treated as request-local and do not participate in the current homogeneous batching policy.
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 ¶
num_running_requests() -> int
Return the number of requests currently running.
abstractmethod ¶
num_waiting_requests() -> int
Return the number of requests waiting to be scheduled.
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.