English
Related papers

Related papers: Salca: A Sparsity-Aware Hardware Accelerator for E…

200 papers

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Machine Learning · Computer Science 2025-04-22 Sushant Singh , Ausif Mahmood

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in…

Computation and Language · Computer Science 2025-06-26 Zhisong Zhang , Yan Wang , Xinting Huang , Tianqing Fang , Hongming Zhang , Chenlong Deng , Shuaiyi Li , Dong Yu

Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence…

Machine Learning · Computer Science 2025-06-02 Xiaodong Ji , Hailin Zhang , Fangcheng Fu , Bin Cui

A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. However, RNNs are fundamentally unable to randomly access…

Computation and Language · Computer Science 2025-11-04 Xiang Hu , Jiaqi Leng , Jun Zhao , Kewei Tu , Wei Wu

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…

Computation and Language · Computer Science 2026-03-30 Yijiong Yu , Shuai Yuan , Jie Zheng , Huazheng Wang , Ji Pei

Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and…

Computation and Language · Computer Science 2026-05-01 Jiaqi Leng , Xiang Hu , Junxiong Wang , Jianguo Li , Wei Wu , Yucheng Lu

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations…

Machine Learning · Computer Science 2025-12-19 Dhruv Deshmukh , Saurabh Goyal , Nipun Kwatra , Ramachandran Ramjee

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

Machine Learning · Computer Science 2024-08-20 Shuo Yang , Ying Sheng , Joseph E. Gonzalez , Ion Stoica , Lianmin Zheng

Large Language Models (LLMs) with expanding context windows face significant performance hurdles. While caching key-value (KV) states is critical for avoiding redundant computation, the storage footprint of long-context caches quickly…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-27 Zhiqiang Xie , Ziyi Xu , Mark Zhao , Yuwei An , Vikram Sharma Mailthody , Scott Mahlke , Michael Garland , Christos Kozyrakis

Transformer-based large language models (LLMs) have achieved remarkable success, yet their standard attention mechanism incurs quadratic computation and memory costs with respect to sequence length, posing a major bottleneck for…

Machine Learning · Computer Science 2025-10-22 Tao Bu , Qiangang Wang , Bowen Zeng , Hanwen Sun , Yunpeng Huang , Chun Cao , Jingwei Xu

The auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. While recent research has investigated various speculative decoding techniques for multi-token generation, these…

Machine Learning · Computer Science 2025-10-01 Hao Mark Chen , Wayne Luk , Ka Fai Cedric Yiu , Rui Li , Konstantin Mishchenko , Stylianos I. Venieris , Hongxiang Fan

The long-context capability of recent large transformer models can be surmised to rely on techniques such as attention/model parallelism, as well as hardware-level optimizations. While these strategies allow input lengths to scale to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Toufiq Parag , Ahmed Elgammal

Large reasoning models achieve strong performance through test-time scaling, but this incurs substantial computational overhead due to long decoding from short prompts. While sparse attention can reduce latency and memory usage, existing…

Computation and Language · Computer Science 2026-04-29 Lijie Yang , Zhihao Zhang , Arti Jain , Shijie Cao , Baihong Yuan , Yiwei Chen , Zhihao Jia , Ravi Netravali

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Computation and Language · Computer Science 2025-06-16 Hanzhi Zhang , Heng Fan , Kewei Sha , Yan Huang , Yunhe Feng

Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length increases; (2) the…

Computation and Language · Computer Science 2025-10-15 Baisub Lee , Sanghyun Byun , Mohanad Odema , Jung Guack , Jacob Song , Woo Seong Chung

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Jongwon Choi , Hyung Jin Chang , Tobias Fischer , Sangdoo Yun , Kyuewang Lee , Jiyeoup Jeong , Yiannis Demiris , Jin Young Choi

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text…

Recently, numerous sparse hardware accelerators for Deep Neural Networks (DNNs), Graph Neural Networks (GNNs), and scientific computing applications have been proposed. A common characteristic among all of these accelerators is that they…