English
Related papers

Related papers: Pie: Pooling CPU Memory for LLM Inference

200 papers

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-31 Zixu Shen , Kexin Chu , Yifan Zhang , Dawei Xiang , Runxin Wu , Wei Zhang

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

Databases · Computer Science 2025-06-30 James Pan , Guoliang Li

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory…

Hardware Architecture · Computer Science 2025-09-15 Huizheng Wang , Zichuan Wang , Zhiheng Yue , Yousheng Long , Taiquan Wei , Jianxun Yang , Yang Wang , Chao Li , Shaojun Wei , Yang Hu , Shouyi Yin

Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-15 Xiangyu Li , Chengyu Yin , Weijun Wang , Jianyu Wei , Ting Cao , Yunxin Liu

Large Language Models (LLMs) are becoming increasingly data-intensive due to growing model sizes, and they are becoming memory-bound as the context length and, consequently, the key-value (KV) cache size increase. Inference, particularly…

Hardware Architecture · Computer Science 2025-11-18 Khyati Kiyawat , Zhenxing Fan , Yasas Seneviratne , Morteza Baradaran , Akhil Shekar , Zihan Xia , Mingu Kang , Kevin Skadron

Large language models (LLMs) suffer from proactive interference (PI): outdated information in the context window disrupts retrieval of current values. This interference degrades retrieval accuracy log-linearly as stale associations…

Artificial Intelligence · Computer Science 2026-03-17 Ying Xie

The data transfer between a processor and memory has become a design bottleneck in data-intensive applications. Processing-In-Memory (PIM) is a practical approach to overcome the memory wall bottleneck. The 4:2 compressor is suitable for…

Emerging Technologies · Computer Science 2024-07-16 Bahareh Bagheralmoosavi , Seyed Erfan Fatemieh , Mohammad Reza Reshadinezhad , Antonio Rubio

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Machine Learning · Computer Science 2025-02-07 Zihao Huang , Qiyang Min , Hongzhi Huang , Defa Zhu , Yutao Zeng , Ran Guo , Xun Zhou

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-01 Chris Tong , Youhe Jiang , Gufeng Chen , Tianyi Zhao , Sibian Lu , Wenjie Qu , Eric Yang , Lynn Ai , Binhang Yuan

As data-intensive applications increasingly strain conventional computing systems, processing-in-memory (PIM) has emerged as a promising paradigm to alleviate the memory wall by minimizing data transfer between memory and processing units.…

Emerging Technologies · Computer Science 2026-02-05 Thomas Neuner , Henriette Padberg , Lior Kornblum , Eilam Yalon , Pedram Khalili Amiri , Shahar Kvatinsky

Large language models (LLMs) hold tremendous potential for addressing numerous real-world challenges, yet they typically demand significant computational resources and memory. Deploying LLMs onto a resource-limited hardware device with…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-02 Pujiang He , Shan Zhou , Changqing Li , Wenhuan Huang , Weifei Yu , Duyi Wang , Chen Meng , Sheng Gui

High Bandwidth Memory with Processing-in-Memory (HBM-PIM) offers an opportunity to reduce data movement by executing computation directly inside memory, but current commercial platforms expose limited instruction sets and require…

Hardware Architecture · Computer Science 2026-05-01 Emanuele Venieri , Simone Manoni , Alberto Florian , Jaehyun Park , Kyomin Sohn , Andrea Bartolini

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

Machine Learning · Computer Science 2026-04-13 Hiroki Matsutani , Naoki Matsuda , Naoto Sugiura

Scaling Large Language Models (LLMs) typically relies on increasing the number of parameters or test-time computations to boost performance. However, these strategies are impractical for edge device deployment due to limited RAM and NPU…

Machine Learning · Computer Science 2026-02-04 Ning Ding , Fangcheng Liu , Kyungrae Kim , Linji Hao , Kyeng-Hun Lee , Hyeonmok Ko , Yehui Tang

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large…

Artificial Intelligence · Computer Science 2024-05-30 Rui Kong , Yuanchun Li , Qingtian Feng , Weijun Wang , Xiaozhou Ye , Ye Ouyang , Linghe Kong , Yunxin Liu

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-19 Zijie Su , Muhammed Tawfiqul Islam , Mohammad Goudarzi , Adel N. Toosi

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their inference efficiency remains a critical bottleneck due to rapidly growing parameters. Recent advances in dynamic computation…

Hardware Architecture · Computer Science 2026-03-17 Zicheng He , Anhao Zhao , Xiaoyu Shen , Chen Wu , Lei He

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key principle underlying the design of PowerInfer is exploiting the high…

Machine Learning · Computer Science 2024-12-13 Yixin Song , Zeyu Mi , Haotong Xie , Haibo Chen

GPU (graphics processing unit) has been used for many data-intensive applications. Among them, deep learning systems are one of the most important consumer systems for GPU nowadays. As deep learning applications impose deeper and larger…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-03-18 Junzhe Zhang , Sai Ho Yeung , Yao Shu , Bingsheng He , Wei Wang