English
Related papers

Related papers: MOM: Memory-Efficient Offloaded Mini-Sequence Infe…

200 papers

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Hardware Architecture · Computer Science 2025-08-13 Ming-Yen Lee , Faaiq Waqar , Hanchen Yang , Muhammed Ahosan Ul Karim , Harsono Simka , Shimeng Yu

Multimodal Large Language Models (MLLMs) are distinguished by their multimodal comprehensive ability and widely used in many real-world applications including GPT-4o, autonomous driving and robotics. Despite their impressive performance,…

Machine Learning · Computer Science 2024-09-17 Zhenyu Ning , Jieru Zhao , Qihao Jin , Wenchao Ding , Minyi Guo

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache,…

Hardware Architecture · Computer Science 2024-09-10 Xiurui Pan , Endian Li , Qiao Li , Shengwen Liang , Yizhou Shan , Ke Zhou , Yingwei Luo , Xiaolin Wang , Jie Zhang

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE)…

Machine Learning · Computer Science 2025-10-07 Hanfei Yu , Xingqi Cui , Hong Zhang , Hao Wang , Hao Wang

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their…

Machine Learning · Computer Science 2025-09-10 Assaf Ben-Kish , Itamar Zimerman , M. Jehanzeb Mirza , Lior Wolf , James Glass , Leonid Karlinsky , Raja Giryes

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

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Machine Learning · Computer Science 2024-12-10 Weizhuo Li , Zhigang Wang , Yu Gu , Ge Yu

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

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

Hardware Architecture · Computer Science 2025-05-06 Yufeng Gu , Alireza Khadem , Sumanth Umesh , Ning Liang , Xavier Servot , Onur Mutlu , Ravi Iyer , Reetuparna Das

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Xiaoniu Song , Zihang Zhong , Rong Chen , Haibo Chen

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Computation and Language · Computer Science 2024-10-15 Guangxuan Xiao , Jiaming Tang , Jingwei Zuo , Junxian Guo , Shang Yang , Haotian Tang , Yao Fu , Song Han

Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices with tight memory constraints. Expert offloading mitigates…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-04 Liujianfu Wang , Yuyang Du , Yuchen Pan , Soung Chang Liew , Jiacheng Liu , Kexin Chen

We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across 16 nodes. Particularly, our method achieves 1M context…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-22 Amy Yang , Jingyi Yang , Aya Ibrahim , Xinfeng Xie , Bangsheng Tang , Grigory Sizov , Jeremy Reizenstein , Jongsoo Park , Jianyu Huang

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in…

Computation and Language · Computer Science 2023-10-11 Yucheng Li , Bo Dong , Chenghua Lin , Frank Guerin

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…

Computation and Language · Computer Science 2025-07-17 Yi Zhao , Zuchao Li , Hai Zhao

External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…

Machine Learning · Computer Science 2026-04-27 Xiucheng Xu , Bingbing Xu , Xueyun Tian , Zihe Huang , Rongxin Chen , Yunfan Li , Huawei Shen

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-18 Bin Xiao , Lei Su

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Computation and Language · Computer Science 2025-09-26 Manlai Liang , Mandi Liu , Jiangzhou Ji , Huaijun Li , Haobo Yang , Yaohan He , Jinlong Li

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making…

Computation and Language · Computer Science 2026-03-17 Lianghui Zhu , Yuxin Fang , Bencheng Liao , Shijie Wang , Tianheng Cheng , Zilong Huang , Chen Chen , Lai Wei , Yutao Zeng , Ya Wang , Yi Lin , Yu Li , Xinggang Wang