WenJie Fan | Searcharxiv

arXiv2026

VestigeKV: The NoPE-MLA KV Cache Carries Its Own Sparse-Attention Signal in a Vestigial Branch

A long-lived KV cache must be compressed before the queries that will read it exist. Selection by observed attention collapses there: on a NoPE-MLA model, H2O and SnapKV retrieve 0.00 and 0.33 of needles at 8x compression, because a token's importance has not yet been observed. VestigeKV instead derives a sparse attention pattern from a signal the cache already carries, occupying the sparse-attention literature's one unoccupied quadrant: training-free and query-independent. In NoPE-MLA the 64-dimensional decoupled branch is a vestige of RoPE that training repurposes into a salience channel; reading 11% of each row, it partitions the cache into an attended tier and a GPU-resident archive that no row ever leaves, reachable each step by a certified, query-adaptive trigger. Nothing is trained and cache rows are never quantized, so every quality effect attributes to selection and scheduling. On Kimi Linear 48B, retrieval holds at 1.00 under 8x and 0.96 under 32x from 8k to 65k context, with zero gap to full-row selection, and the recall tier holds 128x at 1.00 (8k). Both tiers stay on the GPU, so the win is speed, not memory: the per-step scan reads ~26% of the bytes dense attention would, and on a two-node sglang deployment the crossover sits at ~40k context, reaching 1.18x at 256k and 1.39x at 496k. The mechanism is exclusive to NoPE: the identical operator on a RoPE MLA collapses to 0.08, query-independent salience exists only without rotation, and query-universal exact merging is provably impossible under RoPE. All thresholds were frozen before their data; 20 archived verdicts and 8 closed routes accompany the paper.

cs.LG↗

arXiv2026

Q-First: Most of Attention Needs Only the Query in Disaggregated LLM Decoding

Disaggregated LLM serving puts the KV-cache sweep on memory-optimised hardware and the projections and feed-forward on compute-optimised hardware, then inherits from the decoder block a dependency neither device wants: attention runs first and the feed-forward consumes its output, so within one sequence each side idles while the other works. The usual repair costs one resident KV cache per extra sequence in flight, which is what motivated separating the devices at all. We remove the dependency instead. The sweep needs only the query, and exchanging the two sub-layers makes that query available while the compute side still has work to do, so the two run concurrently; the current key and value follow as a cache write nothing waits on. We state the decode as a protocol, show that it runs on stock kernels, and verify it end to end on a trained checkpoint to a relative error of 3.2x10^-3 -- with no new operator, no changed shape and no new hardware. We then train the block 8 ways at two seeds each, varying only where the attention reads and holding everything else fixed. At three per cent of compute-optimal a lead in bits per byte measures how much a change disturbed training rather than what it reaches, so we read magnitudes and not rankings. Among the 5 blocks whose feed-forward does not consume their own attention, no read point differs from the one that moves nothing by more than 0.0026 bits per byte -- smaller than the gap between an arm and itself at a second seed, 0.0066 -- while the same runs resolve a sub-layer exchange 25 times as large. Moving the query early is a change the measurement cannot find, which is what the protocol needs. The reach is bounded: projecting every layer's query from the network's input costs +0.0974, refuting a pre-registered threshold at both seeds, so a query may be read one feed-forward early and no further back.

cs.DC↗