English
Related papers

Related papers: Revisiting Multimodal KV Cache Compression: A Freq…

200 papers

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Machine Learning · Computer Science 2025-11-04 Keqi Deng , Philip C. Woodland

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth. The Key-Value (KV) cache size grows linearly with sequence length…

Machine Learning · Computer Science 2026-05-12 Junkai Zhang , Hang Guo , Luca Benini , Yawei Li

Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However, the nonlinearity introduced by RoPE complicates…

Machine Learning · Computer Science 2025-03-04 Yuhao Zhou , Sirui Song , Boyang Liu , Zhiheng Xi , Senjie Jin , Xiaoran Fan , Zhihao Zhang , Wei Li , Xuanjing Huang

In large language models performing long-form reasoning, the KV cache grows rapidly with decode length, creating bottlenecks in memory and inference stability. Existing reasoning-oriented KV compression has mostly followed an…

Artificial Intelligence · Computer Science 2026-04-14 Buseong Kim , Heejun Gwon

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

Computation and Language · Computer Science 2025-05-27 Tengxuan Liu , Shiyao Li , Jiayi Yang , Tianchen Zhao , Feng Zhou , Xiaohui Song , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Machine Learning · Computer Science 2024-12-18 Hao Kang , Srikant Bharadwaj , James Hensman , Tushar Krishna , Victor Ruhle , Saravan Rajmohan

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Computation and Language · Computer Science 2026-04-09 Zhirui Chen , Peiyang Liu , Ling Shao

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

Machine Learning · Computer Science 2025-04-29 Hanshi Sun , Li-Wen Chang , Wenlei Bao , Size Zheng , Ningxin Zheng , Xin Liu , Harry Dong , Yuejie Chi , Beidi Chen

Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the…

Computation and Language · Computer Science 2025-07-10 Zicong Tang , Shi Luohe , Zuchao Li , Baoyuan Qi , Guoming Liu , Lefei Zhang , Ping Wang

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global…

Machine Learning · Computer Science 2026-05-25 Junzhe Yang , Xiaoyu Shen

KV cache compression methods have mainly relied on scalar quantization techniques to reduce the memory requirements during decoding. In this work, we apply residual vector quantization, which has been widely used for high fidelity audio…

Machine Learning · Computer Science 2024-10-22 Ankur Kumar

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on…

Machine Learning · Computer Science 2026-05-11 Enshuai Zhou , Yifan Hao , Chao Wang , Rui Zhang , Di Huang , Jiaming Guo , Xing Hu , Zidong Du , Qi Guo , Yunji Chen

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

Computation and Language · Computer Science 2025-03-21 Shibo Jie , Yehui Tang , Kai Han , Zhi-Hong Deng , Jing Han

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV cache eviction…

Machine Learning · Computer Science 2026-02-03 Xindian Ma , Yidi Lu , Peng Zhang , Jing Zhang

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Large language models (LLMs) inference relies heavily on KV-caches to accelerate autoregressive decoding, but the resulting memory footprint grows rapidly with sequence length, posing significant efficiency challenges. Current KV-cache…

Databases · Computer Science 2025-09-04 Chenxia Tang , Jianchun Liu , Hongli Xu , Liusheng Huang

KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache.…

Machine Learning · Computer Science 2026-03-31 Bo Jiang , Sian Jin

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising…

Machine Learning · Computer Science 2026-05-18 Andrey Bocharnikov , Ivan Ermakov , Denis Kuznedelev , Vyacheslav Zhdanovskiy , Yegor Yershov

Agentic code tasks such as fault localization and patch generation require processing long codebases under tight memory constraints, where the Key-Value (KV) cache becomes the primary inference bottleneck. Existing compression methods rely…

Computation and Language · Computer Science 2026-04-14 Qiujiang Chen , Jing Xiong , Chenyang Zhao , Sidi Yang , Ngai Wong