English
Related papers

Related papers: MoE-nD: Per-Layer Mixture-of-Experts Routing for M…

200 papers

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wei Tao , Haocheng Lu , Xiaoyang Qu , Bin Zhang , Kai Lu , Jiguang Wan , Jianzong Wang

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Artificial Intelligence · Computer Science 2025-10-01 Yixiao Chen , Yanyue Xie , Ruining Yang , Wei Jiang , Wei Wang , Yong He , Yue Chen , Pu Zhao , Yanzhi Wang

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely hinders their practical deployment. Singular Value…

Machine Learning · Computer Science 2026-02-13 Zhendong Mi , Yixiao Chen , Pu Zhao , Xiaodong Yu , Hao Wang , Yanzhi Wang , Shaoyi Huang

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Machine Learning · Computer Science 2025-09-22 Dmitry Akulov , Mohamed Sana , Antonio De Domenico , Tareq Si Salem , Nicola Piovesan , Fadhel Ayed

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache…

Machine Learning · Computer Science 2026-05-12 Ngoc Bui , Hieu Trung Nguyen , Arman Cohan , Rex Ying

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant…

Machine Learning · Computer Science 2026-03-03 Qian Chen , Xianhao Chen , Kaibin Huang

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and…

Machine Learning · Computer Science 2025-08-08 Xiaodong Chen , Mingming Ha , Zhenzhong Lan , Jing Zhang , Jianguo Li

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM…

Machine Learning · Computer Science 2024-02-29 June Yong Yang , Byeongwook Kim , Jeongin Bae , Beomseok Kwon , Gunho Park , Eunho Yang , Se Jung Kwon , Dongsoo Lee

Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as…

Computation and Language · Computer Science 2024-10-08 Isaac Rehg

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important…

Machine Learning · Computer Science 2026-03-24 Ruijie Miao , Zhiming Wang , Wang Li , Shiwei Wu , Shufan Liu , Yanbing Jiang , Tong Yang

Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation. However, their enormous parameter sizes and memory demands pose…

Machine Learning · Computer Science 2026-02-25 Zukang Xu , Zhixiong Zhao , Xing Hu , Zhixuan Chen , Dawei Yang

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-23 Haodong Wang , Qihua Zhou , Zicong Hong , Song Guo

Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges. Although recent expert merging methods promise greater efficiency by consolidating…

Machine Learning · Computer Science 2025-07-01 Lujun Li , Zhu Qiyuan , Jiacheng Wang , Wei Li , Hao Gu , Sirui Han , Yike Guo

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Machine Learning · Computer Science 2025-12-23 Tao Zhang , Ziqian Zeng , Hao Peng , Huiping Zhuang , Cen Chen

Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth. Existing KV Cache eviction methods primarily rely on local attention weights, neglecting…

Computation and Language · Computer Science 2026-05-11 Tho Mai , Joo-Young Kim

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a…

Machine Learning · Computer Science 2025-03-18 Shwai He , Daize Dong , Liang Ding , Ang Li

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on…

Machine Learning · Computer Science 2026-05-11 Enshuai Zhou , Yifan Hao , Chao Wang , Rui Zhang , Di Huang , Jiaming Guo , Xing Hu , Zidong Du , Qi Guo , Yunji Chen

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV cache eviction…

Machine Learning · Computer Science 2026-02-03 Xindian Ma , Yidi Lu , Peng Zhang , Jing Zhang

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global…

Machine Learning · Computer Science 2026-05-25 Junzhe Yang , Xiaoyu Shen

Large Language Models (LLMs) require substantial computational resources during generation. While the Key-Value (KV) cache significantly accelerates this process by storing attention intermediates, its memory footprint grows linearly with…

Computation and Language · Computer Science 2025-08-05 Yi Su , Quantong Qiu , Yuechi Zhou , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang
‹ Prev 1 2 3 10 Next ›