RIFT：面向草稿模型的 KV Cache 压缩与可压缩性训练

View PDF HTML (experimental)

Abstract:Speculative decoding is a popular decode acceleration method. As such, it is particularly relevant to long-output generation, which requires an increasingly large KV cache. KV cache compression offers a way to constrain costs in long-context drafting. However, compression methods that focus on prefill information can lose relevance as the output length grows. We term this phenomenon decode staleness and show that it degrades draft model accuracy under selection-based KV cache compression. We introduce RIFT, a family of selection-based KV cache compression strategies that balance prefill information and recent generated tokens. We show that refreshing the KV cache selection during token generation significantly improves the drafter's quality at the cost of additional decode latency. To alleviate the refresh costs, we propose an adaptive KV refresh strategy that reduces the number of score calculations while retaining the drafter's quality. We further demonstrate how a compressibility-driven drafter training phase, based on sparse attention masks, can improve the drafter's quality under a compressed KV cache. Combined with compressibility training, RIFT enables Qwen3.5-4B, drafting for Qwen3.5-122B, to retain over 98% of its full-cache acceptance length on 32K-token inputs, 4K-token outputs, and an 8K-token KV cache budget.

Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.31098 [cs.CL]
	(or arXiv:2610.31098v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.31098 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dor Tsur [view email]
[v1] Thu, 22 Oct 2026 11:12:23 UTC (119 KB)