cs.AINov 5, 2026

FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving

Authors: Xuan Wang, Zhuanhao Wu, Tingzhu Fang, Xushi Li, Sicheng Zhang, Zhenyu Yang, Feng Liu, Zhaohui Fan, 

Organizations: Huawei Technologies Co., Ltd · Huawei Ascend Computing Technology Development · Shanghai Jiao Tong University

Abstract

In large language model (LLM) serving systems, the key-value (KV) cache grows linearly with sequence length and concurrency, so long-context inference easily hits the high-bandwidth memory (HBM) capacity wall and results in low concurrency. Offloading the KV cache to host dynamic random-access memory (DRAM) frees HBM space and raises concurrency, but the additional cache management and host-to-device (H2D) load overhead inflates inference latency, higher concurrency fails to translate into effective throughput. We present FlashOffloading, a host-DRAM-centric inference architecture that fully offloads the KV cache in both the prefill and decode phases. FlashOffloading builds rolling HBM cache for prefill, a hot cache for decode, a reverse sparse index with zero extra miss-lookup overhead, and a compute--load overlapped kernel, optimizing KV offloading latency across the entire pipeline and delivering throughput gains under a time-per-output-token (TPOT) service-level objective (SLO). In experiments deploying GLM-5.2 with multi-token prediction (MTP3) speculative decoding on an Ascend910C prefill--decode (PD)-disaggregated platform, FlashOffloading improves prefill throughput by up to 1.38×\times and decode throughput by up to 1.91×\times under a 30 ms TPOT constraint. FlashOffloading is integrated into an open-source serving framework: https://github.com/vllm-project/vllm-ascend/tree/releases/v0.30.0.

Figures & tables

Explore similar work

Sep 28, 2026

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

Long-context LLM serving is increasingly bottlenecked by decode, where large KV caches limit batch size and underutilize GPUs. Sparse KV cache offloading expands effective capacity by storing most historical KV blocks in CPU DRAM and recalling only selected blocks on demand. However, we find that existing offloading systems shift the bottleneck to CPU-GPU recall I/O: recall volume varies widely across layers, decode steps and requests, while headwise sparse selection fragments recalls into many small PCIe transfers. This paper presents PulseInfer, an I/O-centric sparse KV cache offloading system. PulseInfer hides variable recall latency with interruptible layer-wise scheduling, adapts offloading decisions with IO-Adaptive Offloading Admission, and coalesces fragmented transfers using SoloHead sparse selection and a gather-scatter I/O engine. Implemented on SGLang, PulseInfer improves decode throughput by up to 4.7x over SGLang and 2.6x over the best existing offloading baseline, while reducing TPOT by up to 76% and preserving near-lossless accuracy.
May 18, 2026

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this strategy quickly hits a ceiling: sparsity cannot be pushed further without degrading accuracy. As a result, when context length and batch size grow, the volume of KV transfers rises sharply and becomes the dominant source of decoding latency. We present KVDrive, a holistic multi-tier KV cache management system spanning GPU memory, host DRAM, and SSD. Unlike prior work that pursues greater sparsity through algorithmic refinements, KVDrive tackles the problem from a systems perspective - jointly orchestrating cache placement, pipeline scheduling, and cross-tier coordination to sustain high-throughput inference under tight GPU budgets. KVDrive advances three fundamental capabilities: it adapts cache management to attention behavior to maximize reuse and minimize redundant data movement; it restructures the decoding pipeline to overlap I/O- and CPU/GPU compute-bound stages, eliminating stalls across heterogeneous resources; and it harmonizes data movement across memory tiers to unlock scalable long-context inference far beyond GPU and DRAM limits. We have implemented a fully functional prototype of KVDrive and evaluated it on long-context benchmarks with popular LLMs. The system achieves up to 1.74x higher throughput compared to state-of-the-art works while preserving accuracy.
Oct 17, 2026

TideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference

Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing KV cache compression reduces decoding memory but typically requires full-prompt prefill to preserve global context, retaining a high construction peak. Online chunk-level eviction lowers memory earlier but selects before each layer has observed the complete prompt, potentially degrading cache construction and decoding. We present TideKV, an on-GPU cache-construction architecture using layer-major delayed eviction. TideKV processes all prompt chunks within each Transformer layer, retains full-prompt KV only for the active layer, and evicts at layer end. This schedule preserves full-prompt-aware selection while reducing activation and temporary memory. Experiments across multiple computing platforms show that TideKV preserves the inference quality and final cache size of the evaluated compression methods. At 64K on A100, it reduces the construction-time transient footprint by 83.89%. On RTX 4090, it increases time to first token by only 1.06% at 64K and enables 128K prefill. TideKV also completes 128K on Jetson, whereas matched post-prefill compression runs out of memory on both resource-constrained platforms. These results show that delayed layer-end eviction substantially expands feasible context lengths without sacrificing cache utility.