paper-with-me

Papers

LightSeq: A High Performance Inference Library for Transformers

2020-10-23 · NAACL 2021 4 · Xiaohui Wang, Ying Xiong, Yang Wei, Mingxuan Wang, Lei LI

Transformer, BERT and their variants have achieved great success in natural language processing. Since Transformer models are huge in size, serving these models is a challenge for real industrial applications. In this paper, we propose LightSeq, a highly efficient inference library for models in the Transformer family. LightSeq includes a series of GPU optimization techniques to to streamline the computation of neural layers and to reduce memory footprint. LightSeq can easily import models trained using PyTorch and Tensorflow. Experimental results on machine translation benchmarks show that LightSeq achieves up to 14x speedup compared with TensorFlow and 1.4x compared with FasterTransformer, a concurrent CUDA implementation. The code is available at https://github.com/bytedance/lightseq.

📄 PDF Abstract BibTeX arXiv:2010.13887

Code (1)

bytedance/lightseq 공식 구현 tf

Tasks

GPUMachine TranslationTranslationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음

Similar Papers 제목 키워드 기반

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

2021-10-12 · Xiaohui Wang, Yang Wei, Ying Xiong, Guyue Huang 외

Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable …

DecoderGPUMachine TranslationSpeech Recognition+1

MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory

2023-10-25 · NeurIPS 2023 11 · Yinan Liang, Ziwei Wang, Xiuwei Xu, Yansong Tang 외

Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convol…

image-classificationImage Classification

BayesDLL: Bayesian Deep Learning Library

2023-09-22 · Minyoung Kim, Timothy Hospedales

We release a new Bayesian neural network library for PyTorch for large-scale deep networks. Our library implements mainstream approximate Bayesian inference algorithms: variational inference, MC-dropout, stochastic-gradi…

Bayesian InferenceDeep LearningVariational Inference

TorchScale: Transformers at Scale

2022-11-23 · Shuming Ma, Hongyu Wang, Shaohan Huang, Wenhui Wang 외

Large Transformers have achieved state-of-the-art performance across many tasks. Most open-source libraries on scaling Transformers focus on improving training or inference with better parallelization. In this work, we p…

Language ModelingLanguage ModellingMachine TranslationTranslation

Transformers: State-of-the-Art Natural Language Processing

2020-10-01 · EMNLP 2020 11 · Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond 외

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has …

Image ClassificationObject RecognitionSpeech Recognition