English
Related papers

Related papers: Inference-Time Hyper-Scaling with KV Cache Compres…

200 papers

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

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

Machine Learning · Computer Science 2025-12-02 Sai Gokhale , Devleena Das , Rajeev Patwari , Ashish Sirasao , Elliott Delaye

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high computational cost stemming from the thousands of visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sayed Pedram Haeri Boroujeni , Niloufar Mehrabi , Patrick Woods , Gabriel Hillesheim , Abolfazl Razi

Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Davide Bucciarelli , Evelyn Turri , Lorenzo Baraldi , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training…

Computation and Language · Computer Science 2025-06-16 Runheng Liu , Xingchen Xiao , Heyan Huang , Zewen Chi , Zhijing Wu

Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate…

Machine Learning · Computer Science 2024-02-06 Yumeng Wang , Zhenyang Xiao

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side…

Computation and Language · Computer Science 2026-03-13 Zhenxu Tian , Yi Su , Juntao Li , Min Zhang

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yingbing Huang , Tharun Adithya Srikrishnan , Steven K. Reinhardt , Deming Chen

LLM inference is essential for applications like text summarization, translation, and data analysis, but the high cost of GPU instances from Cloud Service Providers (CSPs) like AWS is a major burden. This paper proposes InferSave, a…

Machine Learning · Computer Science 2025-04-17 Kihyun Kim , Jinwoo Kim , Hyunsun Chung , Myung-Hoon Cha , Hong-Yeon Kim , Youngjae Kim

Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the token inputs of Large Language Models (LLMs). However, their…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Kevin Y. Li , Sachin Goyal , Joao D. Semedo , J. Zico Kolter

Large language models face significant cost challenges in long-sequence inference. To address this, reusing historical Key-Value (KV) Cache for improved inference efficiency has become a mainstream approach. Recent advances further enhance…

Machine Learning · Computer Science 2025-08-19 Ziyi Cao , Qingyi Si , Jingbin Zhang , Bingquan Liu

We introduce Lexico, a novel KV cache compression method that leverages sparse coding with a universal dictionary. Our key finding is that key-value cache in modern LLMs can be accurately approximated using sparse linear combination from a…

Machine Learning · Computer Science 2024-12-13 Junhyuck Kim , Jongho Park , Jaewoong Cho , Dimitris Papailiopoulos

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Machine Learning · Computer Science 2025-07-25 Manlai Liang , JiaMing Zhang , Xiong Li , Jinlong Li

Recent advancements in Large Visual Language Models (LVLMs) have gained significant attention due to their remarkable reasoning capabilities and proficiency in generalization. However, processing a large number of visual tokens and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Kai Huang , Hao Zou , Bochen Wang , Ye Xi , Zhen Xie , Hao Wang

Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approaches predominantly rely on query-key attention scores to rank…

Computation and Language · Computer Science 2025-09-19 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Optimizing the Key-Value (KV) cache of the Large Language Model (LLM) has been considered critical to saving the cost of inference. Most of the existing KV-cache compression algorithms attempted to sparsify the sequence of tokens by taking…

Machine Learning · Computer Science 2024-10-11 Zihao Wang , Bin Cui , Shaoduo Gan

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…

Computation and Language · Computer Science 2025-07-17 Yi Zhao , Zuchao Li , Hai Zhao