Bitwise-Identical Latent Reuse for Causal Video Encoders

Causal video encoders recompute shared work across overlapping clips, but pixel overlap alone does not justify feature reuse: independently initialized clips differ in temporal support and sampling phase. We derive compatible reuse regions at multiple encoder depths. Shallow features become reusable earlier; deeper features become reusable later but avoid more computation. ClipStore combines both within a request, preserves request-local suffix state, and retains only planned reads using bounded rolling storage. On a frozen Wan2.1 encoder, all $4,944$ timed output comparisons across four videos match independent encoding exactly. On the reference plan, complete construction takes $9.9\%$ less time and retains $21.9\%$ fewer feature bytes than the faster fixed-cut baseline, with a $2.51\times$ speedup over independent encoding. Request-count, length, overlap, and grouping sweeps identify where source construction is amortized. The reported gain in a 50-step text-to-video pipeline is $1.006\times$; encoder reuse adds no output error when combined with DiT-side caching. Decoder continuation illustrates the complementary use of retained causal state to preserve an existing stream’s outputs.