paper-with-me

Papers

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs

2026-02-07 · Yanlin Qi, Xinhang Chen, Huiqiang Jiang, Qitong Wang, Botao Peng, Themis Palpanas arxiv

KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling on-demand top-$k$ fetching with minimal overhead. ParisKV matches or outperforms full attention quality on long-input and long-generation benchmarks. It achieves state-of-the-art long-context decoding efficiency: it matches or exceeds full attention speed even at batch size 1 for long contexts, delivers up to 2.8$\times$ higher throughput within full attention's runnable range, and scales to million-token contexts where full attention runs out of memory. At million-token scale, ParisKV reduces decode latency by 17$\times$ and 44$\times$ compared to MagicPIG and PQCache, respectively, two state-of-the-art KV-cache Top-$k$ retrieval baselines, code is available at https://github.com/amy-77/ParisKV/tree/main.

📄 PDF Abstract BibTeX arXiv:2602.07721

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference

2026-01-20 · Zhiyuan Shi, Qibo Qiu, Feng Xue, Zhonglin Jiang 외 arxiv

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent …

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

2026-05-26 · Syed Huma Shah arxiv

Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV reuse is now standard in serving stacks such as vLLM, and chunk-leve…

BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation

2025-11-28 · Zeyu Zhang, Jinyuan Mao, Shuning Chang, Yuanyu He 외 arxiv

Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon gene…

Video Generation

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference

2026-05-12 · Alireza Nadali, Patrick Cooper, Ashutosh Trivedi, Alvaro Velasquez arxiv

We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each step, the model processes the next chunk …

SCION: Size-aware Policy Orchestration for Nonstationary Object Caches (Long Paper Version)

2026-03-27 · Qizhi Wang arxiv

Object caches underpin cloud and edge services, but production workloads are heterogeneous, nonstationary, and throughput-constrained. Recent simple non-ML policies such as SIEVE and S3-FIFO set a strong baseline, so any…