English
Related papers

Related papers: Kascade: A Practical Sparse Attention Method for L…

200 papers

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

Vision-Language Large Models (VLLMs) face significant efficiency challenges when processing high-resolution inputs. The quadratic complexity in attention and autoregressive generation, as well as the constantly growing key value (KV) cache…

Multimedia · Computer Science 2025-10-31 Zhonghua Jiang , Kunxi Li , Yiyun Zhou , Sihao Liu , Zhaode Wang , Chengfei lv , Shengyu Zhang

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Yitao Yuan , Chenqi Zhao , Bohan Zhao , Zane Cao , Yongchao He , Wenfei Wu

Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for…

Computation and Language · Computer Science 2026-05-19 Jiwon Song , Dongwon Jo , Beomseok Kang , Jae-Joon Kim

Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improving the inference efficiency of LLMs without requiring…

Computation and Language · Computer Science 2025-12-24 Yanhong Li , Songlin Yang , Shawn Tan , Mayank Mishra , Rameswar Panda , Jiawei Zhou , Yoon Kim

We present Top-Theta (Top-$\theta$) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be calibrated to retain the desired constant number of…

Computation and Language · Computer Science 2025-08-25 Konstantin Berestizshevsky , Renzo Andri , Lukas Cavigelli

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Computation and Language · Computer Science 2025-08-05 Da Ma , Lu Chen , Situo Zhang , Yuxun Miao , Su Zhu , Zhi Chen , Hongshen Xu , Hanqi Li , Shuai Fan , Lei Pan , Kai Yu

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing…

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Chen Zhu , Wei Ping , Chaowei Xiao , Mohammad Shoeybi , Tom Goldstein , Anima Anandkumar , Bryan Catanzaro

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

Computation and Language · Computer Science 2024-08-13 Tsendsuren Munkhdalai , Manaal Faruqui , Siddharth Gopal

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Zhuokun Chen , Jianfei Cai , Bohan Zhuang

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Junyan Li , Delin Chen , Tianle Cai , Peihao Chen , Yining Hong , Zhenfang Chen , Yikang Shen , Chuang Gan

Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM,…

Machine Learning · Computer Science 2026-03-31 Qiuyang Zhang , Kai Zhou , Ding Tang , Kai Lu , Cheng Li , Zhenyu Yang , Peng Xu , Jiguang Wan

We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed point after several inference steps. The convergence time…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Haozhe Liu , Wentian Zhang , Jinheng Xie , Francesco Faccio , Mengmeng Xu , Tao Xiang , Mike Zheng Shou , Juan-Manuel Perez-Rua , Jürgen Schmidhuber

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-07 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Zhiyuan Liu , Chuan Shi , Maosong Sun

Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via post-hoc selection or eviction but overlook the root inefficiency: indiscriminate writing to…

Machine Learning · Computer Science 2026-01-29 Yen-Chieh Huang , Pi-Cheng Hsiu , Rui Fang , Ming-Syan Chen

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Machine Learning · Computer Science 2025-11-20 Jintao Zhang , Chendong Xiang , Haofeng Huang , Jia Wei , Haocheng Xi , Jun Zhu , Jianfei Chen

Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…

Machine Learning · Computer Science 2026-05-28 Adam Zweiger , Xinghong Fu , Han Guo , Yoon Kim
‹ Prev 1 8 9 10 Next ›