paper-with-me

Papers

SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks

2018-07-01 · CVPR 2018 6 · Julian Faraone, Nicholas Fraser, Michaela Blott, Philip H. W. Leong

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or activations during training by approximating their distributions with a limited entry codebook. For very low-precisions, such as binary or ternary networks with 1-8-bit activations, the information loss from quantization leads to significant accuracy degradation due to large gradient mismatches between the forward and backward functions. In this paper, we introduce a quantization method to reduce this loss by learning a symmetric codebook for particular weight subgroups. These subgroups are determined based on their locality in the weight matrix, such that the hardware simplicity of the low-precision representations is preserved. Empirically, we show that symmetric quantization can substantially improve accuracy for networks with extremely low-precision weights and activations. We also demonstrate that this representation imposes minimal or no hardware implications to more coarse-grained approaches. Source code is available at https://www.github.com/julianfaraone/SYQ.

📄 PDF Abstract BibTeX arXiv:1807.00301

Code (1)

julianfaraone/SYQ 공식 구현 tf

Tasks

Quantization

Similar Papers 제목 키워드 기반

MRQ:Support Multiple Quantization Schemes through Model Re-Quantization

2023-08-01 · Manasa Manohara, Sankalp Dayal, Tariq Afzal, Rahul Bakshi 외

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conver…

modelQuantization

How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training

2024-04-25 · Jaeseong You, Minseop Park, Kyunggeun Lee, Seokjun An 외

This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehens…

Quantization

AFPQ: Asymmetric Floating Point Quantization for LLMs

2023-11-03 · Yijia Zhang, Sicheng Zhang, Shijie Cao, Dayou Du 외

Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Altho…

Quantization

AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference

2024-11-15 · Janghwan Lee, Jiwoong Park, Jinseok Kim, Yongjik Kim 외

Scaling Large Language Models (LLMs) with extended context lengths has increased the need for efficient low-bit quantization to manage their substantial computational demands. However, reducing precision to 4 bits freque…

QuantizationQuestion AnsweringVisual Question Answering

CSQ: Centered Symmetric Quantization for Extremely Low Bit Neural Networks

2021-09-29 · Faaiz Asim, Jaewoo Park, Azat Azamat, Jongeun Lee

Recent advances in quantized neural networks (QNNs) are closing the performance gap with the full precision neural networks. However at very low precision (i.e., $\le 3$-bits), QNNs often still suffer significant perform…

Quantization