arXiv:2610.36617v1 Announce Type: cross
Abstract: Mamba-2 compresses all context into a fixed-size recurrent state that dominates decoding memory and bandwidth. Existing compressors quantize state values or prune state coordinates, scoring each channel independently in the native basis. We examine trained Mamba-2 states and find that energy is almost rank-one, but the output does not read the energetic directions: energy concentrates in a bias-like direction accumulated by the recurrence, while the content the output reads lives in a low-dimensional subspace that is not aligned with the state's coordinates. Even output-aware scores are computed coordinate by coordinate, so they miss the directions that determine the input–output map. Compression should therefore target the write–read subspace rather than individual coordinates. We propose \method{}, a post-training transform that instantiates balanced truncation with full controllability and observability Gramians and applies the rotation exactly via Mamba-2's scalar-identity transition. Because the useful rank varies widely across layers, we further introduce HARP, which allocates ranks per layer from the Hankel spectrum and protects retrieval-sensitive layers, improving both perplexity and retrieval over uniform budgets. Calibration takes a single forward pass, an order of magnitude faster than GHOST's released protocol, with lower peak memory. With HARP, \method{} halves the state dimension at an average WikiText-2 perplexity increase of $0.3$ points ($1.8\%$) across 130M–2.7B, versus $1.6$ ($9.3\%$) for GHOST, and the gap widens at 25\% retention.
Abstract: Mamba-2 compresses all context into a fixed-size recurrent state that dominates decoding memory and bandwidth. Existing compressors quantize state values or prune state coordinates, scoring each channel independently in the native basis. We examine trained Mamba-2 states and find that energy is almost rank-one, but the output does not read the energetic directions: energy concentrates in a bias-like direction accumulated by the recurrence, while the content the output reads lives in a low-dimensional subspace that is not aligned with the state's coordinates. Even output-aware scores are computed coordinate by coordinate, so they miss the directions that determine the input–output map. Compression should therefore target the write–read subspace rather than individual coordinates. We propose \method{}, a post-training transform that instantiates balanced truncation with full controllability and observability Gramians and applies the rotation exactly via Mamba-2's scalar-identity transition. Because the useful rank varies widely across layers, we further introduce HARP, which allocates ranks per layer from the Hankel spectrum and protects retrieval-sensitive layers, improving both perplexity and retrieval over uniform budgets. Calibration takes a single forward pass, an order of magnitude faster than GHOST's released protocol, with lower peak memory. With HARP, \method{} halves the state dimension at an average WikiText-2 perplexity increase of $0.3$ points ($1.8\%$) across 130M–2.7B, versus $1.6$ ($9.3\%$) for GHOST, and the gap widens at 25\% retention.
This article has been indexed from cs.AI updates on arXiv.org