paper-with-me

Papers

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective

2024-10-06 · Jinhao Li, Jiaming Xu, Shan Huang, Yonghua Chen, Wen Li, Jun Liu, Yaoxiu Lian, Jiayi Pan, Li Ding, Hao Zhou, Yu Wang, Guohao Dai

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and Llama series are currently the main focus due to their superior algorithmic performance. The advancements in generative LLMs are closely intertwined with the development of hardware capabilities. Various hardware platforms exhibit distinct hardware characteristics, which can help improve LLM inference performance. Therefore, this paper comprehensively surveys efficient generative LLM inference on different hardware platforms. First, we provide an overview of the algorithm architecture of mainstream generative LLMs and delve into the inference process. Then, we summarize different optimization methods for different platforms such as CPU, GPU, FPGA, ASIC, and PIM/NDP, and provide inference results for generative LLMs. Furthermore, we perform a qualitative and quantitative comparison of inference performance with batch sizes 1 and 8 on different hardware platforms by considering hardware power consumption, absolute inference speed (tokens/s), and energy efficiency (tokens/J). We compare the performance of the same optimization methods across different hardware platforms, the performance across different hardware platforms, and the performance of different methods on the same hardware platform. This provides a systematic and comprehensive summary of existing inference acceleration work by integrating software optimization methods and hardware platforms. We point out that three trends (multimodality, inference-time compute, and higher inference energy efficiency) are promising to redefine the capabilities of edge artificial intelligence systems. Our project is available at https://dai.sjtu.edu.cn/project.html.

📄 PDF Abstract BibTeX arXiv:2410.04466

Code (1)

kimho666/llm_hardware_survey 공식 구현

Tasks

CPUGPULanguage ModelingLanguage ModellingLarge Language ModelNatural Language UnderstandingText Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
How do I file a dispute with Expedia?*DisputeFastService How do I file a dispute with Expedia? To file a dispute with Expedia, call +1(888) (829) (0881) OR +1(805) (330) (4056), or use their Help Center to submit your case with…
Attention 설명 없음
WordPiece 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Weight Decay 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Similar Papers 제목 키워드 기반

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

2024-10-31 · Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus 외

Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose signi…

BenchmarkingText Generation

Does Form Follow Function? An Empirical Exploration of the Impact of Deep Neural Network Architecture Design on Hardware-Specific Acceleration

2021-07-08 · Saad Abbasi, Mohammad Javad Shafiee, Ellick Chan, Alexander Wong

The fine-grained relationship between form and function with respect to deep neural network architecture design and hardware-specific acceleration is one area that is not well studied in the research literature, with for…

FormGPUNeural Architecture Search

Efficient Large Language Models with Zero-Shot Adjustable Acceleration

2025-09-01 · Sajjad Kachuee, Mohammad Sharifkhani arxiv

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and duri…

Computational EfficiencyText Generation

Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference

2023-12-23 · Hongzheng Chen, Jiahao Zhang, Yixiao Du, Shaojie Xiang 외

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on tempora…

GPUHigh-Level SynthesisLanguage ModelingLanguage Modelling+1

MIVE: A Minimalist Integer Vector Engine for Softmax LayerNorm and RMSNorm Acceleration

2026-06-16 · Kosmas Alexandridis, Giorgos Dimitrakopoulos arxiv

The rapid growth of Large Language Models (LLMs) has intensified the need for specialized hardware accelerators that can satisfy stringent inference latency and power constraints. Although matrix multiplications dominate…