English
Related papers

Related papers: InstCache: A Predictive Cache for LLM Serving

200 papers

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-17 Dong Liu , Yanxuan Yu

The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…

Hardware Architecture · Computer Science 2025-12-09 Zhongchun Zhou , Chengtao Lai , Yuhang Gu , Wei Zhang

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing…

Computation and Language · Computer Science 2026-03-04 Tianyu Fu , Zihan Min , Hanling Zhang , Jichao Yan , Guohao Dai , Wanli Ouyang , Yu Wang

Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-26 Chao Jin , Zili Zhang , Xuanlin Jiang , Fangyue Liu , Xin Liu , Xuanzhe Liu , Xin Jin

We address LLM serving workloads where repeated requests share a common solution structure but differ in localized constraints, such as output schema, variable names, or numeric constants. Prior caching approaches typically reuse either…

Operating Systems · Computer Science 2026-04-01 Azam Nouri

Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than mere knowledge regurgitation. Leveraging the strong…

Computation and Language · Computer Science 2026-01-08 Shuaiyi Li , Zhisong Zhang , Yang Deng , Chenlong Deng , Tianqing Fang , Hongming Zhang , Haitao Mi , Dong Yu , Wai Lam

Large Language Models (LLMs) process millions of queries daily, making efficient response caching a compelling optimization for reducing cost and latency. However, preserving relevance to user queries using this approach proves difficult…

High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is…

Hardware Architecture · Computer Science 2021-03-30 Majid Jalili , Mattan Erez

Large language models (LLMs) propel the prosperity of interactive AI applications showcased by ChatGPT that demand timely response of inference services. However, LLM inference is computation intensive and memory intensive, and improper…

Networking and Internet Architecture · Computer Science 2025-12-29 Yuqing Yang , Yuedong Xu , Lei Jiao

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill…

Machine Learning · Computer Science 2026-03-17 Yingsheng Geng , Yuchong Gao , Weihong Wu , Guyue Liu , Jiang Liu

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due to the quadratic computational complexity of attention in…

Computation and Language · Computer Science 2025-04-22 Shang Yang , Junxian Guo , Haotian Tang , Qinghao Hu , Guangxuan Xiao , Jiaming Tang , Yujun Lin , Zhijian Liu , Yao Lu , Song Han

Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute…

Machine Learning · Computer Science 2025-09-15 Jenny Y. Huang , Mehul Damani , Yousef El-Kurdi , Ramon Astudillo , Wei Sun

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Junwan Kim , Hyunkyung Bae

Diffusion large language models (dLLMs) present a promising alternative to dominant autoregressive models (ARMs) by the ability of parallel decoding at the expense of substantial computation and memory costs. Specifically, the cache…

Computation and Language · Computer Science 2025-10-13 Jianuo Huang , Yaojie Zhang , Yicun Yang , Benhao Huang , Biqing Qi , Dongrui Liu , Linfeng Zhang

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

Large language models are increasingly deployed in multi-agent workflows. We introduce Prompt Choreography, a framework that efficiently executes LLM workflows by maintaining a dynamic, global KV cache. Each LLM call can attend to an…

Computation and Language · Computer Science 2025-12-30 TJ Bai , Jason Eisner

The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system. This paper enables a novel dynamic KV-Cache…

Computation and Language · Computer Science 2025-04-18 Zihao Zeng , Bokai Lin , Tianqi Hou , Hao Zhang , Zhijie Deng

How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate computational costs, LLMs often employ the KV Cache technique…

Computation and Language · Computer Science 2024-07-23 Zheng Wang , Boxiao Jin , Zhongzhi Yu , Minjia Zhang

In Text-to-SQL tasks, existing LLM-based methods often include extensive database schemas in prompts, leading to long context lengths and increased prefilling latency. While user queries typically focus on recurrent table sets-offering an…

Computation and Language · Computer Science 2026-01-14 Jinbo Su , Yuxuan Hu , Cuiping Li , Hong Chen , Jia Li , Lintao Ma , Jing Zhang

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

Computation and Language · Computer Science 2024-12-09 Ozgur Guldogan , Jackson Kunde , Kangwook Lee , Ramtin Pedarsani