English
Related papers

Related papers: KVSculpt: KV Cache Compression as Distillation

200 papers

Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces. However, as the sequence length grows, the key-value (KV) cache expands linearly, incurring significant memory and…

Computation and Language · Computer Science 2026-02-04 Zican Dong , Peiyu Liu , Junyi Li , Zhipeng Chen , Han Peng , Shuo Wang , Wayne Xin Zhao

The key-value (KV) cache accelerates LLMs decoding by storing KV tensors from previously generated tokens. It reduces redundant computation at the cost of increased memory usage. To mitigate this overhead, existing approaches compress KV…

Machine Learning · Computer Science 2025-07-30 Hao Wang , Ligong Han , Kai Xu , Akash Srivastava

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Machine Learning · Computer Science 2026-01-28 Fangzhou Wu , Sandeep Silwal , Qiuyi , Zhang

Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…

Machine Learning · Computer Science 2025-06-05 Chaoyi Jiang , Lei Gao , Hossein Entezari Zarch , Murali Annavaram

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Computation and Language · Computer Science 2025-06-16 Jie Hu , Shengnan Wang , Yutong He , Ping Gong , Jiawei Yi , Juncheng Zhang , Youhui Bai , Renhai Chen , Gong Zhang , Cheng Li , Kun Yuan

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…

Computation and Language · Computer Science 2024-11-21 Luohe Shi , Hongyi Zhang , Yao Yao , Zuchao Li , Hai Zhao

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…

Computation and Language · Computer Science 2025-06-04 Jialong Wu , Zhenglin Wang , Linhai Zhang , Yilong Lai , Yulan He , Deyu Zhou

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

Growing context lengths in transformer-based language models have made the key-value (KV) cache a critical inference bottleneck. While many KV cache pruning methods have been proposed, they have not yet been adopted in major inference…

Machine Learning · Computer Science 2026-02-04 Simon Jegou , Maximilian Jeblick

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or…

Computation and Language · Computer Science 2025-12-18 Xinye Zhao , Spyridon Mastorakis

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store…

Computation and Language · Computer Science 2024-06-06 Dongjie Yang , XiaoDong Han , Yan Gao , Yao Hu , Shilin Zhang , Hai Zhao

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Computation and Language · Computer Science 2024-06-05 Haoyi Wu , Kewei Tu

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses…

Machine Learning · Computer Science 2025-06-17 Guangda Liu , Chengwei Li , Jieru Zhao , Chenqi Zhang , Minyi Guo

KV cache is a widely used acceleration technique for large language models (LLMs) inference. However, its memory requirement grows rapidly with input length. Previous studies have reduced the size of KV cache by either removing the same…

Computation and Language · Computer Science 2025-01-28 Xingyang He , Jie Liu , Shaowei Chen

Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the cache, but task accuracy alone does not identify why a…

Machine Learning · Computer Science 2026-05-12 Ruijie Zhang , Haozhe Liang , Da Chang , Li Hu , Fanqi Kong , Huaxiao Yin , Yu Li

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…

Computation and Language · Computer Science 2025-11-18 Yixuan Wang , Shiyu Ji , Yijun Liu , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Model quantization has become a crucial technique to address the issues of large memory consumption and long inference times associated with LLMs. Mixed-precision quantization, which distinguishes between important and unimportant…

Machine Learning · Computer Science 2024-10-22 Yifan Tan , Haoze Wang , Chao Yan , Yangdong Deng

Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics and reducing the retention of…

Computation and Language · Computer Science 2025-05-28 Xiabin Zhou , Wenbin Wang , Minyan Zeng , Jiaxian Guo , Xuebo Liu , Li Shen , Min Zhang , Liang Ding

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…

Machine Learning · Computer Science 2024-10-02 Hao Kang , Qingru Zhang , Souvik Kundu , Geonhwa Jeong , Zaoxing Liu , Tushar Krishna , Tuo Zhao