Skip to content

Cache

Cache methods exploit algorithm-level redundancy across adjacent diffusion denoising steps. The latent state changes gradually, so selected intermediate work can be reused when a step is sufficiently similar to a prior step.

The paper frames cache as a cross-step family: the cache agent searches the policy, skip-step schedule, cached state, compensation rule, warmup, and maximum cached-step constraints for each deployment instance.

In Sol-Engine

Pipeline Cache path Role
Cosmos3-Super TeaCache Residual replay across denoising steps
LTX-2.3 Stage-specific cache Part of the full LTX optimization stack
SANA-Video EasyCache Main SANA acceleration component

Methods

Method Open-source status Integration Role in the design space
TeaCache open-source local Cosmos runtime timestep-conditioned residual replay, selected for Cosmos3-Super
EasyCache open-source local SANA runtime runtime-adaptive feature reuse, selected for SANA-Video
TaylorSeer open-source cache-dit adapter feature forecasting with Taylor-series extrapolation
Fixed-step cache open-source local local LTX runtime deterministic fixed-step schedule, selected for LTX-2.3
Cache-DiT / DBCache open-source cache-dit adapter block-level diffusion cache family used as a related cache baseline

Practical notes

  • Cache thresholds trade speed for visual fidelity.
  • Timing should be read from warmup-excluded log lines.
  • Quality checks should compare generated videos, not just total latency.