Skip to content

vllm_omni.diffusion.cache.stepcache.state

Mutable state for step-level DiT velocity caching.

StepCacheState

Per-generation mutable state (skip countdown).

config instance-attribute

config = config

skip_countdown instance-attribute

skip_countdown = 0

reset

reset() -> None

should_run_step

should_run_step(
    prev_predictions: list[tuple[Tensor, ...]],
) -> bool

Return True when the DiT forward should execute at this scheduler step.

trim_history

trim_history(
    prev_predictions: list[tuple[Tensor, ...]],
) -> None