English
Related papers

Related papers: BitDecoding: Unlocking Tensor Cores for Long-Conte…

200 papers

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Hardware Architecture · Computer Science 2025-09-16 Yunhua Fang , Rui Xie , Asad Ul Haq , Linsen Ma , Kaoutar El Maghraoui , Naigang Wang , Meng Wang , Liu Liu , Tong Zhang

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

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

Machine Learning · Computer Science 2025-05-23 Zhihang Cai , Xingjun Zhang , Zhendong Tan , Zheng Wei

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Machine Learning · Computer Science 2026-04-06 Xiangbo Qi , Chaoyi Jiang , Murali Annavaram

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction…

Computation and Language · Computer Science 2026-02-10 Jitai Hao , Qiang Huang , Yaowei Wang , Min Zhang , Jun Yu

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

Machine Learning · Computer Science 2026-05-05 Arnab Sanyal , Gourav Datta , Prithwish Mukherjee , Sandeep P. Chinchali , Michael Orshansky

The extremely high computational and storage demands of large language models have excluded most edge devices, which were widely used for efficient machine learning, from being viable options. A typical edge device usually only has 4GB of…

Hardware Architecture · Computer Science 2025-02-18 Jindong Li , Tenglong Li , Guobin Shen , Dongcheng Zhao , Qian Zhang , Yi Zeng

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…

Computation and Language · Computer Science 2025-10-24 Yu Fu , Zefan Cai , Abedelkadir Asi , Wayne Xiong , Yue Dong , Wen Xiao

Large Language Models (LLMs) confront significant memory challenges due to the escalating KV cache with increasing sequence length. As a crucial technique, existing cross-layer KV cache sharing methods either necessitate modified model…

Machine Learning · Computer Science 2025-08-25 Yixuan Wang , Haoyu Qiao , Lujun Li , Qingfu Zhu , Wanxiang Che

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Network (FFN) weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-11 Nidhi Bhatia , Ankit More , Ritika Borkar , Tiyasa Mitra , Ramon Matas , Ritchie Zhao , Maximilian Golub , Dheevatsa Mudigere , Brian Pharris , Bita Darvish Rouhani

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

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

Machine Learning · Computer Science 2024-10-22 Luning Wang , Shiyao Li , Xuefei Ning , Zhihang Yuan , Shengen Yan , Guohao Dai , Yu Wang

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or…

Hardware Architecture · Computer Science 2024-10-17 Lian Liu , Haimeng Ren , Long Cheng , Zhaohui Xu , Yudong Pan , Mengdi Wang , Xiaowei Li , Yinhe Han , Ying Wang

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Computation and Language · Computer Science 2025-10-10 Wenhao Li , Yuxin Zhang , Gen Luo , Haiyuan Wan , Ziyang Gong , Fei Chao , Rongrong Ji

The rapid scaling of Large Language Models (LLMs) elevates inference costs and compounds substantial deployment barriers. While quantization to 8 or 4 bits mitigates this, sub-3-bit methods face severe accuracy, scalability, and efficiency…

‹ Prev 1 4 5 6 7 8 10 Next ›