English
Related papers

Related papers: MAGE: All-[MASK] Block Already Knows Where to Look…

200 papers

Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, making it attractive for efficient inference. However, many…

Large language models (LLMs) have demonstrated remarkable proficiency in a wide range of natural language processing applications. However, the high energy and latency overhead induced by the KV cache limits the edge deployment, especially…

Performance · Computer Science 2025-12-09 Zizhuo Fu , Xiaotian Guo , Wenxuan Zeng , Shuzhang Zhong , Yadong Zhang , Peiyu Chen , Runsheng Wang , Le Ye , Meng Li

Existing methods for training LLMs on long-sequence data, such as Tensor Parallelism and Context Parallelism, exhibit low Model FLOPs Utilization as sequence lengths and number of GPUs increase, especially when sequence lengths exceed 1M…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-25 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Zhiyuan Liu , Chuan Shi , Maosong sun

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

Machine Learning · Computer Science 2025-05-27 Dan Peng , Zhihui Fu , Zewen Ye , Zhuoran Song , Jun Wang

Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer time to first token (TTFT). This bottleneck can be…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Tharun Adithya Srikrishnan , Deval Shah , Timothy Hein , Ahmed Hasssan , Stephen Youn , Steven K. Reinhardt

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Sabiha Afroz , Redwan Ibne Seraj Khan , Hadeel Albahar , Jingoo Han , Ali R. Butt

Long-context Multimodal Large Language Models (MLLMs) that incorporate long text-image and text-video modalities, demand substantial resources as their multimodal Key-Value (KV) caches grow with increasing input lengths, challenging…

Computation and Language · Computer Science 2025-03-14 Zhongwei Wan , Hui Shen , Xin Wang , Che Liu , Zheda Mai , Mi Zhang

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create…

Computation and Language · Computer Science 2025-03-13 Guangtao Wang , Shubhangi Upasani , Chen Wu , Darshan Gandhi , Jonathan Li , Changran Hu , Bo Li , Urmish Thakker

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…

Machine Learning · Computer Science 2025-11-07 Donghyeon Joo , Helya Hosseini , Ramyad Hadidi , Bahar Asgari

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

Computation and Language · Computer Science 2025-12-08 Tianyi Li , Mingda Chen , Bowei Guo , Zhiqiang Shen

The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant…

Computation and Language · Computer Science 2024-07-19 Bingli Liao , Danilo Vasconcellos Vargas

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Enis Simsar , Alessio Tonioni , Yongqin Xian , Thomas Hofmann , Federico Tombari

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Mohsen Ghafoorian , Denis Korzhenkov , Amirhossein Habibian

Diffusion models represent a powerful family of generative models widely used for image and video generation. However, the time-consuming deployment, long inference time, and requirements on large memory hinder their applications on…

Machine Learning · Computer Science 2025-04-18 Kafeng Wang , Jianfei Chen , He Li , Zhenpeng Mi , Jun Zhu

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory…

Computation and Language · Computer Science 2024-06-24 Jincheng Dai , Zhuowei Huang , Haiyun Jiang , Chen Chen , Deng Cai , Wei Bi , Shuming Shi

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…

Machine Learning · Computer Science 2024-10-02 Hao Kang , Qingru Zhang , Souvik Kundu , Geonhwa Jeong , Zaoxing Liu , Tushar Krishna , Tuo Zhao

We introduce Block-attention, an attention mechanism designed to address the increased inference latency and cost in Retrieval-Augmented Generation (RAG) scenarios. Traditional approaches often encode the entire context in an…

Machine Learning · Computer Science 2025-04-15 Dongyang Ma , Yan Wang , Lan Tian

The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significant GPU under-utilization. This paper introduces Mixture of…

Machine Learning · Computer Science 2025-11-11 Myunghyun Rhee , Sookyung Choi , Euiseok Kim , Joonseop Sim , Youngpyo Joo , Hoshik Kim

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Aiyue Chen , Yaofu Liu , Junjian Huang , Guang Lian , Yiwu Yao , Wangli Lan , Jing Lin , Zhixin Ma , Tingting Zhou