English
Related papers

Related papers: FastAttention: Extend FlashAttention2 to NPUs and …

200 papers

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-12 Zifan He , Rui Ma , Yizhou Sun , Jason Cong

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

Hardware Architecture · Computer Science 2025-04-25 Qingyuan Liu , Liyan Chen , Yanning Yang , Haocheng Wang , Dong Du , Zhigang Mao , Naifeng Jing , Yubin Xia , Haibo Chen

We revisit the I/O complexity of attention in large language models. Given query-key-value matrices $Q,K,V\in\mathbb{R}^{n\times d}$, and a machine with fast memory size $M$, the goal is to compute the "attention matrix" $A=\text{softmax}(Q…

Machine Learning · Computer Science 2026-05-25 Pál András Papp , Aleksandros Sobczyk , Anastasios Zouzias

Recent Super-Resolution~(SR) methods mainly adopt Transformers for their strong long-range modeling capability and exceptional representational capacity. However, most SR Transformers rely heavily on relative positional bias~(RPB), which…

Machine Learning · Computer Science 2026-03-10 Dongheon Lee , Seokju Yun , Jaegyun Im , Youngmin Ro

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context generation. While existing approaches offload KV caches to CPU…

Machine Learning · Computer Science 2025-07-08 Weishu Deng , Yujie Yang , Peiran Du , Lingfeng Xiang , Zhen Lin , Chen Zhong , Song Jiang , Hui Lu , Jia Rao

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are…

Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must attend to as they generate new ones. To address this…

Computation and Language · Computer Science 2024-04-16 Tian Jin , Wanzin Yazar , Zifei Xu , Sayeh Sharify , Xin Wang

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

Computation and Language · Computer Science 2025-12-16 Coleman Hooper , Sebastian Zhao , Luca Manolache , Sehoon Kim , Michael W. Mahoney , Yakun Sophia Shao , Kurt Keutzer , Amir Gholami

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

Machine Learning · Computer Science 2024-09-05 Luka Ribar , Ivan Chelombiev , Luke Hudlass-Galley , Charlie Blake , Carlo Luschi , Douglas Orr

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xianbing Sun , Zhikai Zhu , Zhengyu Lou , Bo Yang , Jinyang Tang , Liqing Zhang , He Wang , Jianfu Zhang

To efficiently support Large Language Models (LLMs), modern GPGPU architectures have introduced new features and programming paradigms, such as warp specialization. These features enable temporal overlap between the producer and consumer,…

Hardware Architecture · Computer Science 2026-05-05 Zhongchun Zhou , Yuhang Gu , Chengtao Lai , Ya Wang , Wei Zhang

Huawei's openPangu-Embedded-1B and openPangu-Embedded-7B are variants of the openPangu large language model, designed for efficient deployment on Ascend NPUs. The 7B variant supports three distinct Chain-of-Thought (CoT) reasoning…

Machine Learning · Computer Science 2026-01-09 Yilun Luo , Huaqing Zheng , Haoqian Meng , Wenyuan Liu , Peng Zhang

Transformer-based models dominate modern AI workloads but exacerbate memory bottlenecks due to their quadratic attention complexity and ever-growing model sizes. Existing accelerators, such as Groq and Cerebras, mitigate off-chip traffic…

Hardware Architecture · Computer Science 2026-02-12 Jinxin Yu , Yudong Pan , Mengdi Wang , Huawei Li , Yinhe Han , Xiaowei Li , Ying Wang

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

Computation and Language · Computer Science 2023-12-19 Bingchen Zhao , Haoqin Tu , Chen Wei , Jieru Mei , Cihang Xie

This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In Stage 1, query and key sequences are compressed into coarse…

Signal Processing · Electrical Eng. & Systems 2026-05-13 Chong Wu , Zhenan Feng , Renjie Xu , Houwang Zhang , Jiawang Cao , Maolin Che , Wenbo Zhu , Hong Yan

Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenecks at long sequences. A key challenge is to design foundation models that maintain…

The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational…

‹ Prev 1 8 9 10 Next ›