English
Related papers

Related papers: QuantSpec: Self-Speculative Decoding with Hierarch…

200 papers

Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving. Quantizing the KV cache to fewer bits…

Machine Learning · Computer Science 2026-05-11 Fei Zuo , Zikang Zhou , Hao Cong , Xiaoyan Xi , Ho Fai Leung

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

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

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by…

Large language models (LLMs) have gained great success in various domains. Existing systems cache Key and Value within the attention block to avoid redundant computations. However, the size of key-value cache (KV cache) is unpredictable and…

Hardware Architecture · Computer Science 2025-05-26 Peilin Chen , Xiaoxuan Yang

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Computation and Language · Computer Science 2024-06-05 Heming Xia , Zhe Yang , Qingxiu Dong , Peiyi Wang , Yongqi Li , Tao Ge , Tianyu Liu , Wenjie Li , Zhifang Sui

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Xihao Chen , Yangyang Guo , Roger Zimmermann

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Operating Systems · Computer Science 2026-01-21 Jing Zou , Shangyu Wu , Hancong Duan , Qiao Li , Chun Jason Xue

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV)…

Machine Learning · Computer Science 2026-05-07 Chengyi Nie , Nian Si , Zijie Zhou

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

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

Cloud-based Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for…

Computation and Language · Computer Science 2026-01-13 Kaiyu Huang , Hao Wu , Zhubo Shi , Han Zou , Minchen Yu , Qingjiang Shi

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Machine Learning · Computer Science 2026-04-06 Xiangbo Qi , Chaoyi Jiang , Murali Annavaram

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high…

Computation and Language · Computer Science 2025-04-03 Ranajoy Sadhukhan , Jian Chen , Zhuoming Chen , Vashisth Tiwari , Ruihang Lai , Jinyuan Shi , Ian En-Hsu Yen , Avner May , Tianqi Chen , Beidi Chen

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper…

Databases · Computer Science 2025-10-01 Jang-Hyun Kim , Jinuk Kim , Sangwoo Kwon , Jae W. Lee , Sangdoo Yun , Hyun Oh Song

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Computation and Language · Computer Science 2025-02-06 You Wu , Haoyi Wu , Kewei Tu

As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge. Yet using long contexts is challenging, as nothing can be generated until the whole context is…

Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native…

Machine Learning · Computer Science 2025-06-10 Pengxiang Zhao , Xiaoming Yuan

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or…

Computation and Language · Computer Science 2025-12-18 Xinye Zhao , Spyridon Mastorakis