numpy

Two phases of N-1 steps each, a chunk index that rotates with the step, and a byte count that should come out to exactly the textbook formula. The implementation, the verification against a direct sum, and the measured traffic matching 2(N-1)/N times the message at every rank count tested.

Follow the matrix shapes through a low-rank update. Verify merged inference numerically and show why multiplying sums of adapter factors gives the wrong weights.

Build a small CPU reference, overwrite a bounded KV ring, and compare every step with a recomputed attention window. Keep model semantics separate from eviction.

Derive the scale, handle zero tensors, clamp before casting, and separate rounding error from clipping. Compare one outlier under tensor and channel scales.