cs.DCNov 17, 2026

XM-Sparse: High-Throughput Sparse-Attention LLM Serving over Scale-up Memory Pools

Authors: Yijun Sun, Xudong Liao, Zhuobin Huang, Kai Chen, Nikita Lazarev, Zhizhen Zhong

Organizations: Netpreme · The Hong Kong University of Science and Technology · National University of Singapore

Abstract

Sparse attention has been increasingly adopted by production LLMs for long-context inference, yet serving systems must still retain the full KV history, making GPU HBM capacity a key limit on serving concurrency. Existing systems offload the KV cache to host memory, but suffer from the limited bandwidth of PCIe and the limited capacity of host memory. Emerging scale-up memory pools (e.g., X-Mem) relieve both limits and open new opportunities for sparse-attention offloading. In this paper, we first conduct an in-depth analysis and reveal that, even with scale-up memory pools, decode throughput remains bounded by HBM capacity, as hot KV buffers and the fully resident indexer key (K-index) cache occupy substantial HBM. Moreover, the two caches exhibit distinct access patterns. Based on these insights, we present XM-Sparse, the first sparse-attention offloading system over scale-up memory expansion. The core idea of XM-Sparse is to offload both caches aggressively while matching each with an I/O mechanism tailored to its access pattern. Specifically, for dynamically selected KV entries, XM-Sparse fuses TMA-based retrieval with attention in a tile-level pipeline to hide on-demand retrieval latency. For predictable K-index accesses, it prefetches pages via SM-efficient GPU-initiated DMA and coordinates prefetching with latency-critical operations to avoid interfering with decoding. We have implemented XM-Sparse atop SGLang, and our experiments on DeepSeek-V3.2 and GLM-5.3 with an emulated scale-up memory pool show that XM-Sparse delivers up to 4.98×\times and 4.52×\times higher decode throughput than PCIe-based ECHO and HiSparse, respectively, and up to 1.34×\times over a naive integration on the same platform, across 16K-1M contexts.

Figures & tables

Explore similar work

CardsList
  1. Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

    Apr 29, 2026Zihan Zhao, Baotong Lu, Shengjie Lin +8LLM ServingKV-Cache Offloading

  2. PulseInfer: I/O-Centric Sparse KV Cache Offloading for Efficient Long-Context LLM Decoding

    Sep 28, 2026Qiuyang Zhang, Kai Zhou, Kai Lu +6KV-Cache OffloadingLong-Context Language Model Inference

  3. SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

    Jun 3, 2026Yaosheng Fu, Guangxuan Xiao, Xin Dong +2KV-Cache OffloadingLong-Context Language Model Inference