English
Related papers

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

200 papers

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Machine Learning · Computer Science 2026-01-28 Fangzhou Wu , Sandeep Silwal , Qiuyi , Zhang

KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache.…

Machine Learning · Computer Science 2026-03-31 Bo Jiang , Sian Jin

Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, this router is trained once and then frozen, rendering routing…

Computation and Language · Computer Science 2026-05-26 Boxuan Lyu , Soichiro Murakami , Hidetaka Kamigaito , Peinan Zhang

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

Machine Learning · Computer Science 2025-05-27 Shibo Jie , Yehui Tang , Kai Han , Yitong Li , Duyu Tang , Zhi-Hong Deng , Yunhe Wang

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Computation and Language · Computer Science 2025-08-05 Da Ma , Lu Chen , Situo Zhang , Yuxun Miao , Su Zhu , Zhi Chen , Hongshen Xu , Hanqi Li , Shuai Fan , Lei Pan , Kai Yu

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Computation and Language · Computer Science 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

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

Large language models (LLMs) have recently shown strong potential in audio-visual speech recognition (AVSR), but their high computational demands and sensitivity to token granularity limit their practicality in resource-constrained…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Umberto Cappellazzo , Minsu Kim , Pingchuan Ma , Honglie Chen , Xubo Liu , Stavros Petridis , Maja Pantic

An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subset of them. During autoregressive generation, these models…

Machine Learning · Computer Science 2025-11-05 Costin-Andrei Oncescu , Qingyang Wu , Wai Tong Chung , Robert Wu , Bryan Gopal , Junxiong Wang , Tri Dao , Ben Athiwaratkun

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the…

Computation and Language · Computer Science 2026-04-28 Zahra Dehghanighobadi , Asja Fischer

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

Machine Learning · Computer Science 2026-02-10 Jang-Hyun Kim , Dongyoon Han , Sangdoo Yun

Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating multiple experts per…

Machine Learning · Computer Science 2025-10-14 Wei Huang , Yue Liao , Yukang Chen , Jianhui Liu , Haoru Tan , Si Liu , Shiming Zhang , Shuicheng Yan , Xiaojuan Qi

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Machine Learning · Computer Science 2026-01-21 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Hai Zhao , Xiaoming Fu

Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences. Existing eviction methods typically retain KV pairs with…

Computation and Language · Computer Science 2026-05-12 Yongqi An , Chang Lu , Kuan Zhu , Tao Yu , Chaoyang Zhao , Hong Wu , Ming Tang , Jinqiao Wang

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

Large Language Models (LLMs) with Mixture-of-Experts (MoE) architectures are distinguished by their strong performance scaling with increasing parameters across a wide range of tasks, yet they also suffer from substantial computational and…

Computation and Language · Computer Science 2025-11-27 Yuzhuang Xu , Xu Han , Yuanchi Zhang , Yixuan Wang , Yijun Liu , Shiyu Ji , Qingfu Zhu , Wanxiang Che

Mixture-of-Experts (MoE) models scale capacity efficiently, but their massive parameter footprint creates a deployment-time memory bottleneck. We organize retraining-free MoE compression into three paradigms - Expert Pruning, Expert…

Machine Learning · Computer Science 2026-03-04 Sieun Hyeon , Jaeyoung Do

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Artificial Intelligence · Computer Science 2025-08-05 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

The proliferation of large language models (LLMs) has driven the adoption of Mixture-of-Experts (MoE) architectures as a promising solution to scale model capacity while controlling computational costs. However, deploying MoE models in…

Networking and Internet Architecture · Computer Science 2025-08-14 Muqing Li , Ning Li , Xin Yuan , Wenchao Xu , Quan Chen , Song Guo , Haijun Zhang