ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
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.
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
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?
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
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 GenerationKV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
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)
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…