English
Related papers

Related papers: GORGO: Maximizing KV-Cache Reuse While Minimizing …

200 papers

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-23 Xingyu Xiang , Raj Joshi , Yuhan Liu , Jiayi Yao , Chenxingyu Zhao , Junchen Jiang , Yang Zhou , Eddie Kohler , Minlan Yu

Large language model (LLM) inference systems face a fundamental tension between minimizing Time-to-First-Token (TTFT) latency for new requests and maintaining a high, steady token generation rate (low Time-Per-Output-Token, or TPOT) for…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-17 Hongtao Lyu , Boyue Liu , Mingyu Wu , Haibo Chen

The growing demand for efficient Large Language Model (LLM) inference requires a holistic optimization on algorithms, systems, and hardware. However, very few works have fundamentally changed the generation pattern: each token needs one…

Computation and Language · Computer Science 2025-05-28 Jingyu Liu , Ce Zhang

Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill stage, which processes the full input context to construct Key-Value (KV) caches. We…

Networking and Internet Architecture · Computer Science 2026-05-06 Hongyao Liu , Liuqun Zhai , Junyi Wang , Zhengru Fang

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Machine Learning · Computer Science 2024-04-09 Muhammad Adnan , Akhil Arunkumar , Gaurav Jain , Prashant J. Nair , Ilya Soloveychik , Purushotham Kamath

Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single…

Machine Learning · Computer Science 2026-05-08 Mikhail Shirokikh , Sergey Nikolenko

Congestion control is vastly important in computer networks. Arising naturally from the bursty nature of Internet traffic, congestion plagues not only the network edge, but also the network core. Many remedies have been proposed to fight…

Networking and Internet Architecture · Computer Science 2020-07-06 Christen Ford

With the reduction of satellite costs and the enhancement of processing capabilities, low earth orbit (LEO) satellite constellations can independently build inter-satellite networks without relying on traditional ground stations restricted…

Networking and Internet Architecture · Computer Science 2022-09-28 Xue Sun , Changhao Li , Lei Yan , Suzhi Cao

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…

Machine Learning · Computer Science 2026-03-03 Ngoc Bui , Shubham Sharma , Simran Lamba , Saumitra Mishra , Rex Ying

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

As large language models (LLMs) proliferate in scale, specialization, and latency profiles, the challenge of routing user prompts to the most appropriate model has become increasingly critical for balancing performance and cost. We…

Software Engineering · Computer Science 2025-09-19 Amine Barrak , Yosr Fourati , Michael Olchawa , Emna Ksontini , Khalil Zoghlami

Although vision transformers (ViT) have shown remarkable success in various vision tasks, their computationally expensive self-attention hinder their deployment on resource-constrained devices. Token reduction, which discards less important…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Haoyue Zhang , Jie Zhang , Song Guo

Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…

Machine Learning · Computer Science 2025-06-05 Chaoyi Jiang , Lei Gao , Hossein Entezari Zarch , Murali Annavaram

Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only through lightweight adapters. Despite sharing base model weights, each agent independently builds and…

Machine Learning · Computer Science 2026-02-03 Hyesung Jeon , Hyeongju Ha , Jae-Joon Kim

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

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

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token…

Databases · Computer Science 2025-09-18 Dongwei Wang , Zijie Liu , Song Wang , Yuxin Ren , Jianing Deng , Jingtong Hu , Tianlong Chen , Huanrui Yang

Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike…

Computation and Language · Computer Science 2026-01-27 Zihan Wang , Cheng Tang , Lei Gong , Cheng Li , Chao Wang , teng wang , Wenqi Lou , Xuehai Zhou

Transformer-based large language models (LLMs) are now deployed to hundreds of millions of users. LLM inference is commonly performed on batches of sequences that share a prefix, such as few-shot examples or a chatbot system prompt.…

Machine Learning · Computer Science 2024-05-14 Jordan Juravsky , Bradley Brown , Ryan Ehrlich , Daniel Y. Fu , Christopher Ré , Azalia Mirhoseini

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-19 Jiaao He , Jidong Zhai