View PDF HTML (experimental)

Abstract:In long-context LLM serving, the prefill stage often dominates time-to-first-token and computational cost. Although Prefix Cache in vLLM/PagedAttention has been widely used to reuse identical prompt prefixes, repeated content in practical applications frequently appears as non-prefix, cross-request, cross-turn, and cross-agent segments, which makes conventional cache mechanisms insufficient. This paper presents SparseX, a segment-level KV Cache sharing method for common serving scenarios. SparseX uses contiguous token segments as reuse units and exploits Sparse-Q indices that naturally arise in KV Cache reuse workloads to estimate the key tokens that require correction. Based on this estimate, SparseX performs Sparse-KV Recomputation within a single forward pass, thereby restoring cross-segment contextual interactions under complex interleaved reuse patterns while avoiding additional models or separate preprocessing stages for token selection. SparseX further implements a full+sparse hybrid attention mode based on a layer-specific threshold: early layers retain full attention to obtain a more stable token-importance signal, and later layers switch to sparse recomputation to improve reuse quality on complex long-context tasks. We implement SparseX-vLLM on top of vLLM, integrating segment-level cache lookup, PagedAttention management, RoPE alignment, Sparse-Q token selection, and FlashAttention backends into a unified execution path. SparseX is model-agnostic, training-free, and compatible with Prefix Cache, and it provides unified support for common online serving scenarios including multi-round chat, retrieval-augmented generation (RAG), and agent workflows.

Submission history

From: Quqing Zhang [view email]
[v1] Mon, 1 Jun 2026 06:12:55 UTC (6,143 KB)