English
Related papers

Related papers: Hybrid JIT-CUDA Graph Optimization for Low-Latency…

200 papers

Graph neural networks (GNNs) have delivered remarkable results in various fields. However, the rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference. Both computational complexity and…

Machine Learning · Computer Science 2025-03-11 Xiabao Wu , Yongchao Liu , Wei Qin , Chuntao Hong

With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…

Machine Learning · Computer Science 2025-12-02 Agrim Bari , Parikshit Hegde , Gustavo de Veciana

This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed with key data about the desired task, such as agent action abilities, and the desired end…

Robotics · Computer Science 2026-05-18 Swayamjit Saha , Subhabrata Das , Haonan Duan , Xiao-Yang Liu

We present Thinking While Driving, a concurrent routing framework that integrates LLMs into a graph-based traffic environment. Unlike approaches that require agents to stop and deliberate, our system enables LLM-based route planning while…

Multiagent Systems · Computer Science 2025-12-12 Xiaopei Tan , Muyang Fan

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

Hardware Architecture · Computer Science 2025-07-15 Chun-Ting Chen , HanGyeol Mun , Jian Meng , Mohamed S. Abdelfattah , Jae-sun Seo

Just-in-time (JIT) compilers are used by many modern programming systems in order to improve performance. Bugs in JIT compilers provide exploitable security vulnerabilities and debugging them is difficult as they are large, complex, and…

Programming Languages · Computer Science 2021-08-27 HeuiChan Lim , Stephen Kobourov

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…

Machine Learning · Computer Science 2025-03-14 Shaobo Ma , Chao Fang , Haikuo Shao , Zhongfeng Wang

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine Learning · Computer Science 2025-10-02 Anushka Tiwari , Sayantan Pal , Rohini K. Srihari , Kaiyi Ji

Running Large Language Models (LLMs) on edge devices is constrained by high compute and memory demands posing a barrier for real-time applications in sectors like healthcare, education, and embedded systems. Current solutions such as…

Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start latency remains a major bottleneck. While recent systems have reduced model weight…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-09 Xueshen Liu , Yongji Wu , Yuncheng Yao , Danyang Zhuo , Ion Stoica , Z. Morley Mao

Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed…

Neural and Evolutionary Computing · Computer Science 2025-05-20 Ziyao Huang , Weiwei Wu , Kui Wu , Jianping Wang , Wei-Bin Lee

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Performance · Computer Science 2024-03-05 Xuanlei Zhao , Bin Jia , Haotian Zhou , Ziming Liu , Shenggan Cheng , Yang You

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

Computation and Language · Computer Science 2024-04-26 In Gim , Guojun Chen , Seung-seob Lee , Nikhil Sarda , Anurag Khandelwal , Lin Zhong

Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit…

Computation and Language · Computer Science 2026-01-08 Xin Zhang , Kailai Yang , Hao Li , Chenyue Li , Qiyu Wei , Sophia Ananiadou

Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory…

Machine Learning · Computer Science 2024-11-12 Jinhao Li , Jiaming Xu , Shiyao Li , Shan Huang , Jun Liu , Yaoxiu Lian , Guohao Dai

Computer-use agents (CUA) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click, type, and scroll on a browser. Current implementations follow…

Machine Learning · Computer Science 2026-05-21 Caleb Winston , Ron Yifeng Wang , Azalia Mirhoseini , Christos Kozyrakis

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-29 Mingyu Sun , Xiao Zhang , Shen Qu , Yan Li , Mengbai Xiao , Yuan Yuan , Dongxiao Yu

This paper introduces an efficient Vision-Language Model (VLM) pipeline specifically optimized for deployment on embedded devices, such as those used in robotics and autonomous driving. The pipeline significantly reduces the computational…

Machine Learning · Computer Science 2025-11-04 Jin Huang , Yuchao Jin , Le An , Josh Park