English
Related papers

Related papers: Unifying Sparse Attention with Hierarchical Memory…

200 papers

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…

Machine Learning · Computer Science 2026-04-10 Jiaming Cheng , Duong Tung Nguyen

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

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yuxiang Huang , Mingye Li , Xu Han , Chaojun Xiao , Weilin Zhao , Ao Sun , Ziqi Yuan , Hao Zhou , Fandong Meng , Zhiyuan Liu

Learned sparse retrieval (LSR) is a popular method for first-stage retrieval because it combines the semantic matching of language models with efficient CPU-friendly algorithms. Previous work aggregates blocks into "superblocks" to quickly…

Information Retrieval · Computer Science 2026-02-04 Parker Carlson , Wentai Xie , Rohil Shah , Tao Yang

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-08 Bin Lin , Chen Zhang , Tao Peng , Hanyu Zhao , Wencong Xiao , Minmin Sun , Anmin Liu , Zhipeng Zhang , Lanbo Li , Xiafei Qiu , Shen Li , Zhigang Ji , Tao Xie , Yong Li , Wei Lin

Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM) streaming rather than arithmetic. Existing methods such as…

Machine Learning · Computer Science 2026-05-27 Anay Chauhan , Gurucharan Marthi Krishna Kumar , Arion Das , Amit Dhanda , Vinija Jain , Aman Chadha , Amitava Das

Sparse matrix-vector multiplication (SpMV) operations are commonly used in various scientific applications. The performance of the SpMV operation often depends on exploiting regularity patterns in the matrix. Various representations have…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-07-25 Karan Aggarwal , Uday Bondhugula

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Computation and Language · Computer Science 2026-03-03 Samhruth Ananthanarayanan , Ayan Sengupta , Tanmoy Chakraborty

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Machine Learning · Computer Science 2026-05-29 Wenhao Dai , Haodong Deng , Mengfei Rong , Xinyu Yang , Hongyu Liu , Fangxin Liu , Hailong Yang , Qianwen Cao , Qingxiao Sun

The memory-for-computation paradigm of KV caching is essential for accelerating large language model (LLM) inference service, but limited GPU high-bandwidth memory (HBM) capacity motivates offloading the KV cache to cheaper external storage…

With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Arun Ramachandran , Ramaswamy Govindarajan , Murali Annavaram , Prakash Raghavendra , Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

Hardware Architecture · Computer Science 2026-03-11 Jianlong Lei , Shashikant Ilager

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-23 Jiale Xu , Rui Zhang , Cong Guo , Weiming Hu , Zihan Liu , Feiyang Wu , Yu Feng , Shixuan Sun , Changxu Shao , Yuhong Guo , Junping Zhao , Ke Zhang , Minyi Guo , Jingwen Leng

Pipeline Parallelism (PP) serves as a crucial technique for training Large Language Models (LLMs), owing to its capability to alleviate memory pressure from model states with relatively low communication overhead. However, in long-context…

Machine Learning · Computer Science 2025-04-22 Zhouyang Li , Yuliang Liu , Wei Zhang , Tailing Yuan , Bin Chen , Chengru Song , Di Zhang

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Computation and Language · Computer Science 2026-01-07 Junxiang Qiu , Shuo Wang , Zhengsu Chen , Hengheng Zhang , Jinda Lu , Changcheng Li , Qi Tian

Emerging machine learning (ML) models (e.g., transformers) involve memory pin bandwidth-bound matrix-vector (MV) computation in inference. By avoiding pin crossings, processing in memory (PIM) can improve performance and energy for…

Hardware Architecture · Computer Science 2024-04-09 Mingxuan He , Mithuna Thottethodi , T. N. Vijaykumar

State-of-the-art Learned Sparse Retrieval (LSR) models, such as Splade, typically employ a Language Modeling (LM) head to project latent hidden states into a lexically-anchored logit matrix. This intermediate matrix is subsequently…

Information Retrieval · Computer Science 2026-03-27 Thong Nguyen , Cosimo Rulli , Franco Maria Nardini , Rossano Venturini , Andrew Yates