paper-with-me

Papers

Efficient Remote KV Cache Reuse with GPU-native Video Codec

2026-02-10 · Liang Mi, Weijun Wang, Jinghan Chen, Ting Cao, Haipeng Dai, Yunxin Liu arxiv

Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While it excels in high-speed networks, its performance degrades significantly in bandwidth-limited scenarios. Recent studies address this by transmitting KV caches in compressed form, but the associated heavyweight decompression counteracts the KV reuse benefits. In this paper, we propose an efficient and widely deployable remote KV cache reuse solution that leverages GPU-native video codecs. Our system, KVCodec, enables effective KV cache coding with two techniques. The codec-friendly tensor layout compresses the KV cache in a highly compact video format, enabling fast transmission. The efficient KV fetcher orchestrates the transmission, decoding, and restoration of compressed KV caches in an efficient pipelined manner, eliminating resource contention, masking network fluctuations, and achieving minimum time-to-first-token (TTFT). We prototype KVCodec on diverse GPUs from high- to low-end. Experiments reveal that it reduces TTFT by up to 3.51 times while maintaining lossless accuracy, compared to SOTA methods.

📄 PDF Abstract BibTeX arXiv:2602.09725

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference

2026-04-07 · Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park 외 arxiv

Continuous inference over concurrent video streams imposes substantial compute and memory demands on vision-language model (VLM) serving. Streaming inference uses sliding windows to maintain a bounded context of recent v…

Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers

2026-07-16 · James O' Neill, Fergal Reid arxiv

Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step. We show that this loop-indexed cache is highly structured. For a fixed toke…

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

2024-10-25 · Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang 외

In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based metho…

Video Generation

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching

2025-09-17 · Hanshuai Cui, Zhiqing Tang, Zhifei Xu, Zhi Yao 외 arxiv

Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiti…

Video Generation

VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs

2026-07-16 · Shahrzad Esmat, Dhawal Shah, Ali Jannesari arxiv

The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference. Two leading training-free families are both structurally limited: token-selection methods (SnapKV, Ada-KV) scor…