English
Related papers

Related papers: Towards Fully 8-bit Integer Inference for the Tran…

200 papers

The past several years have witnessed the success of transformer-based models, and their scale and application scenarios continue to grow aggressively. The current landscape of transformer models is increasingly diverse: the model size…

For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep token representations efficiently. Our architecture uses a…

Computation and Language · Computer Science 2020-02-07 Sachin Mehta , Rik Koncel-Kedziorski , Mohammad Rastegari , Hannaneh Hajishirzi

Transformer models gain popularity because of their superior inference accuracy and inference throughput. However, the transformer is computation-intensive, causing a long inference time. The existing works on transformer inference…

Performance · Computer Science 2023-04-19 Yuan Feng , Hyeran Jeon , Filip Blagojevic , Cyril Guyot , Qing Li , Dong Li

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into low-bitwidth numbers without significant accuracy…

Machine Learning · Computer Science 2024-02-14 Jiajun Zhou , Jiajun Wu , Yizhao Gao , Yuhao Ding , Chaofan Tao , Boyu Li , Fengbin Tu , Kwang-Ting Cheng , Hayden Kwok-Hay So , Ngai Wong

State-of-the-art neural machine translation methods employ massive amounts of parameters. Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful. To this end, we propose…

Computation and Language · Computer Science 2020-03-24 Gabriele Prato , Ella Charlaix , Mehdi Rezagholizadeh

Recently, the idea of using FP8 as a number format for neural network training has been floating around the deep learning world. Given that most training is currently conducted with entire networks in FP32, or sometimes FP16 with…

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating point (FP8) binary interchange format consisting of two…

Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or…

Machine Learning · Computer Science 2021-09-10 Ye Lin , Yanyang Li , Tong Xiao , Jingbo Zhu

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

The creation of practical deep learning data-products often requires parallelization across processors and computers to make deep learning feasible on large data sets, but bottlenecks in communication bandwidth make it difficult to attain…

Neural and Evolutionary Computing · Computer Science 2016-02-22 Tim Dettmers

Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. To address this issue, researchers have proposed multiplication-free neural networks, such as…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Xinlin Li , Bang Liu , Rui Heng Yang , Vanessa Courville , Chao Xing , Vahid Partovi Nia

Recently, the Transformer machine translation system has shown strong results by stacking attention layers on both the source and target-language sides. But the inference of this model is slow due to the heavy use of dot-product attention…

Computation and Language · Computer Science 2019-06-27 Tong Xiao , Yinqiao Li , Jingbo Zhu , Zhengtao Yu , Tongran Liu

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be…

Machine Learning · Computer Science 2017-12-19 Benoit Jacob , Skirmantas Kligys , Bo Chen , Menglong Zhu , Matthew Tang , Andrew Howard , Hartwig Adam , Dmitry Kalenichenko

Tokenization is widely used in large language models because it significantly improves performance. However, tokenization imposes several disadvantages, such as performance biases, increased adversarial vulnerability, decreased…

Computation and Language · Computer Science 2024-10-08 Kevin Slagle

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Computation and Language · Computer Science 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it exposes the softmax as the dominant bottleneck. This stage incurs…

Machine Learning · Computer Science 2025-11-27 Wanli Zhong , Haibo Feng , Zirui Zhou , Hanyang Peng , Shiqi Yu

This paper presents the design of a hardware accelerator for Transformers, optimized for on-device time-series forecasting in AIoT systems. It integrates integer-only quantization and Quantization-Aware Training with optimized hardware…

Machine Learning · Computer Science 2026-04-22 Tianheng Ling , Chao Qian , Gregor Schiele