paper-with-me

Papers

Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers

2019-05-30 · Manuele Rusci, Alessandro Capotondi, Luca Benini

This paper presents a novel end-to-end methodology for enabling the deployment of low-error deep networks on microcontrollers. To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the inference graph with integer-only operations. Our approach aims at determining the minimum bit precision of every activation and weight tensor given the memory constraints of a device. This is achieved through a rule-based iterative procedure, which cuts the number of bits of the most memory-demanding layers, aiming at meeting the memory constraints. After a quantization-aware retraining step, the fake-quantized graph is converted into an inference integer-only model by inserting the Integer Channel-Normalization (ICN) layers, which introduce a negligible loss as demonstrated on INT4 MobilenetV1 models. We report the latency-accuracy evaluation of mixed-precision MobilenetV1 family networks on a STM32H7 microcontroller. Our experimental results demonstrate an end-to-end deployment of an integer-only Mobilenet network with Top1 accuracy of 68% on a device with only 2MB of FLASH memory and 512kB of RAM, improving by 8% the Top1 accuracy with respect to previously published 8 bit implementations for microcontrollers.

📄 PDF Abstract BibTeX arXiv:1905.13082

Code (2)

mrusci/training-mixed-precision-quantized-networks 공식 구현 pytorch
EEESlab/CMix-NN

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models

2026-02-01 · Xin Nie, Haicheng Zhang, Liang Dong, Beining Feng 외 arxiv

Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either r…

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

2026-05-21 · Jianing Deng, Song Wang, Dongwei Wang, Zijie Liu 외 arxiv

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert…

KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache

2025-05-18 · Fei Li, Song Liu, Weiguo Wu, Shiqiang Nie 외

The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the me…

Quantization

ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs

2026-02-06 · Xinlin Li, Timothy Chou, Josh Fromm, Zichang Liu 외 arxiv

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight…

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost

2025-11-23 · Haojun Xia, Xiaoxia Wu, Jisen Li, Robert Wu 외 arxiv

The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-…