中文
相关论文

相关论文: Understanding the Performance and Power of LLM Inf…

200 篇论文

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

硬件体系结构 · 计算机科学 2026-02-10 Xiaoyu Ma , David Patterson

The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to cloud GPU clusters. Benchmarking is crucial for optimizing…

分布式、并行与集群计算 · 计算机科学 2025-12-12 Hung-Yueh Chiang , Bokun Wang , Diana Marculescu

Large Language Models (LLMs) like GPT and LLaMA are revolutionizing the AI industry with their sophisticated capabilities. Training these models requires vast GPU clusters and significant computing time, posing major challenges in terms of…

Modern large language models (LLMs) driven by scaling laws, achieve intelligence emergency in large model sizes. Recently, the increasing concerns about cloud costs, latency, and privacy make it an urgent requirement to develop compact edge…

机器学习 · 计算机科学 2025-02-13 Xingrun Xing , Zheng Liu , Shitao Xiao , Boyan Gao , Yiming Liang , Wanpeng Zhang , Haokun Lin , Guoqi Li , Jiajun Zhang

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

计算与语言 · 计算机科学 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein

As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost, and personalization. This survey explores a collaborative…

分布式、并行与集群计算 · 计算机科学 2025-07-23 Senyao Li , Haozhao Wang , Wenchao Xu , Rui Zhang , Song Guo , Jingling Yuan , Xian Zhong , Tianwei Zhang , Ruixuan Li

The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source…

机器学习 · 计算机科学 2024-03-20 Anique Tahir , Lu Cheng , Huan Liu

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

计算与语言 · 计算机科学 2025-06-03 Zeping Min , Jinbo Wang

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

分布式、并行与集群计算 · 计算机科学 2024-07-23 Jiale Xu , Rui Zhang , Cong Guo , Weiming Hu , Zihan Liu , Feiyang Wu , Yu Feng , Shixuan Sun , Changxu Shao , Yuhong Guo , Junping Zhao , Ke Zhang , Minyi Guo , Jingwen Leng

Large language models (LLMs) are increasingly used in applications forming multi-request workflows like document summarization, search-based copilots, and multi-agent programming. While these workflows unlock richer functionality, they also…

分布式、并行与集群计算 · 计算机科学 2026-04-14 Md. Monzurul Amin Ifath , Israat Haque

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

硬件体系结构 · 计算机科学 2025-05-06 Yufeng Gu , Alireza Khadem , Sumanth Umesh , Ning Liang , Xavier Servot , Onur Mutlu , Ravi Iyer , Reetuparna Das

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

硬件体系结构 · 计算机科学 2025-04-23 Rui Xie , Asad Ul Haq , Linsen Ma , Yunhua Fang , Zirak Burzin Engineer , Liu Liu , Tong Zhang

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them…

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Gautom Das , Vincent La , Ethan Lau , Abhinav Shrivastava , Matthew Gwilliam

Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges…

分布式、并行与集群计算 · 计算机科学 2024-04-05 Qinghao Hu , Zhisheng Ye , Zerui Wang , Guoteng Wang , Meng Zhang , Qiaoling Chen , Peng Sun , Dahua Lin , Xiaolin Wang , Yingwei Luo , Yonggang Wen , Tianwei Zhang

Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardware resources available in such environments. While embedded…

硬件体系结构 · 计算机科学 2025-10-20 Jindong Li , Tenglong Li , Ruiqi Chen , Guobin Shen , Dongcheng Zhao , Qian Zhang , Yi Zeng

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

机器学习 · 计算机科学 2024-11-06 Jiedong Lang , Zhehao Guo , Shuyu Huang

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

机器学习 · 计算机科学 2025-09-03 Zixi Chen , Yinyu Ye , Zijie Zhou

This paper explores the seamless integration of Generative AI (GenAI) and Evolutionary Algorithms (EAs) within the domain of large-scale multi-objective optimization. Focusing on the transformative role of Large Language Models (LLMs), our…

神经与进化计算 · 计算机科学 2024-05-14 Gaurav Singh , Kavitesh Kumar Bali

Large language models have been widely adopted but require significant GPU memory for inference. We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory…

机器学习 · 计算机科学 2022-11-11 Tim Dettmers , Mike Lewis , Younes Belkada , Luke Zettlemoyer