Dual-QK：用于可剪枝 2-bit KV Cache 的锐利查询与平坦键

View PDF HTML (experimental)

Abstract:Long inputs and extended generation increase the storage and access costs of the key-value (KV) cache. Low-bit quantization reduces storage and memory traffic, while query-channel pruning can further reduce key-cache reads. Rotation-based quantization redistributes the energy of key outliers across channels. To maintain computational invariance, the same orthogonal transform must be applied to queries, preserving query-key dot products. However, this rotation can disperse query energy, weakening the separation between a few large components to retain and many small ones to prune. We introduce Dual-QK, which uses paired non-orthogonal query and key transforms to address this conflict. Using calibrated query and key statistics, Dual-QK combines partial key whitening with a query-aligned basis to balance key scales for INT2 quantization and concentrate query energy for dynamic channel pruning. Channel-0 protection and bucket-relative RoPE support low-bit accuracy over long contexts. Experiments on four models across five generative benchmarks and long-context retrieval tasks show improved accuracy over OSCAR on most tasks at 40% query-channel sparsity. At a 128K context, Dual-QK provides $6.8\times$ KV-cache compression and an estimated $8.3\times$ reduction in KV read volume relative to unpruned BF16. Under the evaluated configurations, our SGLang implementation achieves up to $3.75\times$ the decoding throughput of unpruned BF16.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.09827 [cs.LG]
	(or arXiv:2610.09827v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.09827 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sunjoo Whang [view email]
[v1] Wed, 7 Oct 2026 10:50:06 UTC (1,654 KB)