English
Related papers

Related papers: TRACE: Unlocking Effective CXL Bandwidth via Lossl…

200 papers

Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…

Computation and Language · Computer Science 2025-10-13 Yu-Chen Lu , Chong-Yan Chen , Chi-Chih Chang , Yu-Fang Hu , Kai-Chiang Wu

During the training of Large Language Models (LLMs), tensor data is periodically "checkpointed" to persistent storage to allow recovery of work done in the event of failure. The volume of data that must be copied during each checkpoint,…

Machine Learning · Computer Science 2025-05-16 Daniel Waddington , Cornel Constantinescu

The proliferation of data-intensive applications, ranging from large language models to key-value stores, increasingly stresses memory systems with mixed read-write access patterns. Traditional half-duplex architectures such as DDR5 are…

Operating Systems · Computer Science 2025-08-25 Yiwei Yang , Yusheng Zheng , Yiqi Chen , Zheng Liang , Kexin Chu , Zhe Zhou , Andi Quinn , Wei Zhang

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Machine Learning · Computer Science 2025-12-09 Sourjya Roy , Shrihari Sridharan , Surya Selvam , Anand Raghunathan

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this…

Computation and Language · Computer Science 2026-05-19 Jian Lin , Jiazhi Mi , Zicong Hong , Haodong Wang , Qianli Liu , Haodyue Zhang , Peng Li , Song Guo

Recent Serverless workloads tend to be largescaled/CPU-memory intensive, such as DL, graph applications, that require dynamic memory-to-compute resources provisioning. Meanwhile, recent solutions seek to design page management strategies…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-09-26 Yuze Li , Shunyu Yao

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-12 Yipin Guo , Siddharth Joshi

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these…

Machine Learning · Computer Science 2024-07-02 Ceyu Xu , Yongji Wu , Xinyu Yang , Beidi Chen , Matthew Lentz , Danyang Zhuo , Lisa Wu Wills

Large language models (LLMs) training or inference across multiple nodes introduces significant pressure on GPU memory and interconnect bandwidth. The Compute Express Link (CXL) shared memory pool offers a scalable solution by enabling…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Dong Xu , Han Meng , Xinyu Chen , Dengcheng Zhu , Wei Tang , Fei Liu , Liguang Xie , Wu Xiang , Rui Shi , Yue Li , Henry Hu , Hui Zhang , Jianping Jiang , Dong Li

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit…

Machine Learning · Computer Science 2025-03-12 Erik Wijmans , Brody Huval , Alexander Hertzberg , Vladlen Koltun , Philipp Krähenbühl

Modern large language models (LLMs) drive interactive AI systems but are bottlenecked by the memory-heavy growth of key-value (KV) caches, which limits real-time throughput under concurrent loads. Existing KV-cache compression methods rely…

Machine Learning · Computer Science 2026-01-07 Joseph Kampeas , Emir Haleva

With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands.…

Hardware Architecture · Computer Science 2025-10-22 Ye Qiao , Zhiheng Chen , Yifan Zhang , Yian Wang , Sitao Huang

Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-19 Ruibo Fan , Xiangrui Yu , Xinglin Pan , Zeyu Li , Weile Luo , Qiang Wang , Wei Wang , Xiaowen Chu

Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards…

Computation and Language · Computer Science 2025-10-06 Jingqi Zhang , Ruibo Chen , Yingqing Yang , Peihua Mai , Heng Huang , Yan Pang

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

Cryptography and Security · Computer Science 2026-05-19 Xinwei Zhang , Hangcheng Liu , Li Bai , Hao Wang , Qingqing Ye , Tianwei Zhang , Haibo Hu

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

Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as…

Computation and Language · Computer Science 2024-10-08 Isaac Rehg

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR).…

Machine Learning · Computer Science 2018-02-07 Markus Kliegl , Siddharth Goyal , Kexin Zhao , Kavya Srinet , Mohammad Shoeybi