Image de couverture de livre

BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Yongqi, Lee, Yujian, Yi, Gao, Liu, Bosheng, Chen, Yucong, Liu, Peng, Wu, Jigang, Chen, Xiaoming, Han, Yinhe
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PIMCOMP: An End-to-End DNN Compiler for Processing-In-Memory Accelerators
par: Sun, Xiaotian, et autres
Publié: (2024)

A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training
par: Ali, Sami Ben, et autres
Publié: (2024)

LLM-FP4: 4-Bit Floating-Point Quantized Transformers
par: Liu, Shih-yang, et autres
Publié: (2023)

Range, Not Precision: Block-Floating-Point Half-Precision FFT and SAR Imaging on Apple Silicon
par: Bergach, Mohamed Amine
Publié: (2026)

How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?
par: Lee, Yujian, et autres
Publié: (2026)

Search Your Block Floating Point Scales!
par: Gupta, Tanmaey, et autres
Publié: (2026)

SlimEdge: Performance and Device Aware Distributed DNN Deployment on Resource-Constrained Edge Hardware
par: Kumar, Mahadev Sunil, et autres
Publié: (2025)

Fragments of Martin's axiom
par: Peng, Yinhe
Publié: (2025)

A ccc indestructible construction with CH
par: Peng, Yinhe
Publié: (2025)

Distinguishing Martin's axiom from its restrictions
par: Peng, Yinhe
Publié: (2024)

Reduced Floating-Point Precision Implicit Monte Carlo
par: Butson, Simon, et autres
Publié: (2025)

Precision Arithmetic: A New Floating-Point Arithmetic
par: Wang, Chengpu
Publié: (2006)

Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices
par: Lee, Hayun, et autres
Publié: (2024)

The AetherFloat Family: Block-Scale-Free Quad-Radix Floating-Point Architectures for AI Accelerators
par: Morisaki, Keita
Publié: (2026)

PIMSIM-NN: An ISA-based Simulation Framework for Processing-in-Memory Accelerators
par: Wang, Xinyu, et autres
Publié: (2024)

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
par: Chen, Yanzuo, et autres
Publié: (2023)

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
par: Choi, Kanghyun, et autres
Publié: (2025)

Precision-Aware Iterative Algorithms Based on Group-Shared Exponents of Floating-Point Numbers
par: Gao, Jianhua, et autres
Publié: (2024)

Accurate Reduced Floating-Point Precision Implicit Monte Carlo
par: Butson, Simon, et autres
Publié: (2025)

WebAssembly on Resource-Constrained IoT Devices: Performance, Efficiency, and Portability
par: Has, Mislav, et autres
Publié: (2025)

F-BFQ: Flexible Block Floating-Point Quantization Accelerator for LLMs
par: Haris, Jude, et autres
Publié: (2025)

Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices
par: Ye, Shengyuan, et autres
Publié: (2024)

Camel: Energy-Aware LLM Inference on Resource-Constrained Devices
par: Xu, Hao, et autres
Publié: (2025)

Asymmetric Catalytic Aziridination to Synthesize Spiro‐aziridine Oxindoles
par: Yinhe Qu, et autres
Publié: (2025)

decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
par: Guo, Yi, et autres
Publié: (2024)

Floating Solar Materials and their Devices for Energy Conversion and Environment Remediation
par: Xinyi Liu, et autres
Publié: (2024)

Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
par: Manamperi, Lakshani, et autres
Publié: (2026)

Optimizing Digital Signal Processing with Half-Precision Floating-Point Arithmetic
par: Dr. Elianore Quasar and Dr. Kaia Rykhard
Publié: (2019)

Clock Skew Compensation Algorithm Immune to Floating-Point Precision Loss
par: Kim, Kyeong Soo, et autres
Publié: (2021)

Double-Precision Floating-Point Data Visualizations Using Vulkan API
par: Sozen, Nezihe
Publié: (2024)

Bit Transition Reduction by Data Transmission Ordering in NoC-based DNN Accelerator
par: Chen, Yizhi, et autres
Publié: (2025)

Mixed-Precision in High-Order Methods: the Impact of Floating-Point Precision on the ADER-DG Algorithm
par: Marot-Lassauzaie, Marc, et autres
Publié: (2025)

Precise Regulation of Excited‐State Intramolecular Proton‐Transfer Materials for High‐Efficiency Monochromatic and White‐emitting OLEDs
par: Tao Yang, et autres
Publié: (2024)

Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices
par: Chen, Fahao, et autres
Publié: (2025)

DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
par: Liu, Renyuan, et autres
Publié: (2025)

Polynomial Invariant Generation for Floating-Point Programs
par: Cai, Xuran, et autres
Publié: (2025)

FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search
par: Dotzel, Jordan, et autres
Publié: (2023)

TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction
par: Li, Yuhang, et autres
Publié: (2024)

Enlightenment Period Improving DNN Performance
par: Liu, Tiantian, et autres
Publié: (2025)

Do Standard Neural Networks Show RG-like Advantages on Local Block-Spin Maps?
par: Liu, Xiaoming
Publié: (2026)