paper-with-me

홈 › Papers

A Survey of Techniques for Optimizing Transformer Inference

2023-07-16 · Krishna Teja Chitty-Venkata, Sparsh Mittal, Murali Emani, Venkatram Vishwanath, Arun K. Somani

Recent years have seen a phenomenal rise in performance and applications of transformer neural networks. The family of transformer networks, including Bidirectional Encoder Representations from Transformer (BERT), Generative Pretrained Transformer (GPT) and Vision Transformer (ViT), have shown their effectiveness across Natural Language Processing (NLP) and Computer Vision (CV) domains. Transformer-based networks such as ChatGPT have impacted the lives of common men. However, the quest for high predictive performance has led to an exponential increase in transformers' memory and compute footprint. Researchers have proposed techniques to optimize transformer inference at all levels of abstraction. This paper presents a comprehensive survey of techniques for optimizing the inference phase of transformer networks. We survey techniques such as knowledge distillation, pruning, quantization, neural architecture search and lightweight network design at the algorithmic level. We further review hardware-level optimization techniques and the design of novel hardware accelerators for transformers. We summarize the quantitative results on the number of parameters/FLOPs and accuracy of several models/techniques to showcase the tradeoff exercised by them. We also outline future directions in this rapidly evolving field of research. We believe that this survey will educate both novice and seasoned researchers and also spark a plethora of research efforts in this field.

📄 PDF Abstract BibTeX arXiv:2307.07982

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationNeural Architecture SearchQuantizationSurvey

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Full Stack Optimization of Transformer Inference: a Survey

2023-02-27 · Sehoon Kim, Coleman Hooper, Thanakul Wattanawong, Minwoo Kang 외

Recent advances in state-of-the-art DNN architecture design have been moving toward Transformer models. These models achieve superior accuracy across a wide range of applications. This trend has been consistent over the …

Neural Architecture SearchSchedulingSurvey

Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies

2025-02-26 · Shaibal Saha, Lanyu Xu

In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networ…

image-classificationImage ClassificationModel Compressionobject-detection+1

Optimizing Inference in Transformer-Based Models: A Multi-Method Benchmark

2025-09-22 · Siu Hang Ho, Prasad Ganesan, Nguyen Duong, Daniel Schlabig arxiv

Efficient inference is a critical challenge in deep generative modeling, particularly as diffusion models grow in capacity and complexity. While increased complexity often improves accuracy, it raises compute costs, late…

Knowledge Distillation

Comprehensive Survey of Model Compression and Speed up for Vision Transformers

2024-04-16 · Feiyang Chen, Ziqian Luo, Lisang Zhou, Xueting Pan 외

Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory dema…

Computational EfficiencyEdge-computingKnowledge DistillationModel Compression+1

Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques

2025-05-05 · Sanjay Surendranath Girija, Shashank Kapoor, Lakshit Arora, Dipen Pradhan 외

Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a com…

Knowledge DistillationMixture-of-ExpertsModel CompressionQuantization