Image de couverture de livre

M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hu, Weiming, Zhang, Haoyan, Guo, Cong, Feng, Yu, Guan, Renyang, Hua, Zhendong, Liu, Zihan, Guan, Yue, Guo, Minyi, Leng, Jingwen
Format:	Preprint
Publié:	2025
Sujets:	Hardware Architecture
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization
par: Hu, Weiming, et autres
Publié: (2026)

Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations
par: Feng, Yu, et autres
Publié: (2024)

SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity
par: Li, Xingyang, et autres
Publié: (2025)

StreamGrid: Streaming Point Cloud Analytics via Compulsory Splitting and Deterministic Termination
par: Feng, Yu, et autres
Publié: (2025)

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy
par: Feng, Yu, et autres
Publié: (2025)

Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture
par: Feng, Yu, et autres
Publié: (2024)

Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing
par: Huang, Xiaotong, et autres
Publié: (2025)

An Optimizing Framework on MLIR for Efficient FPGA-based Accelerator Generation
par: Zhang, Weichuang, et autres
Publié: (2024)

KANtize: Exploring Low-bit Quantization of Kolmogorov-Arnold Networks for Efficient Inference
par: Errabii, Sohaib, et autres
Publié: (2026)

Design of a 6-bit Threshold Inverter Quantization (TIQ) Flash Analog to Digital Converter (ADC)
par: Sarkar, Noyon Kumar, et autres
Publié: (2025)

bitSMM: A bit-Serial Matrix Multiplication Accelerator
par: Antunes, Pedro, et autres
Publié: (2026)

Gaze into the Pattern: Characterizing Spatial Patterns with Internal Temporal Correlations for Hardware Prefetching
par: Chen, Zixiao, et autres
Publié: (2024)

Single 32-bit Sub-Channel DDR5 DIMMs: Architecture, Performance Bounds, and Standardisation
par: Ke, Chih-Hua
Publié: (2026)

Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
par: Zhang, Chen, et autres
Publié: (2026)

CoQMoE: Co-Designed Quantization and Computation Orchestration for Mixture-of-Experts Vision Transformer on FPGA
par: Dong, Jiale, et autres
Publié: (2025)

AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs
par: Gao, Mingzhe, et autres
Publié: (2024)

Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication
par: Shan, Haoxuan, et autres
Publié: (2025)

TMA-Adaptive FP8 Grouped GEMM: Eliminating Padding Requirements in Low-Precision Training and Inference on Hopper
par: Su, Zhongling, et autres
Publié: (2025)

Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression
par: Cheng, Feng, et autres
Publié: (2025)

CODO: An Automated Compiler for Comprehensive Dataflow Optimization
par: Zhang, Weichuang, et autres
Publié: (2026)

Enabling Efficient Transaction Processing on CXL-Based Memory Sharing
par: Wang, Zhao, et autres
Publié: (2025)

Sensitivity-Aware Mixed-Precision Quantization for ReRAM-based Computing-in-Memory
par: Chen, Guan-Cheng, et autres
Publié: (2025)

D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs
par: Abdelmaksoud, Ahmed J., et autres
Publié: (2026)

Hardware-Efficient Accurate 4-bit Multiplier for Xilinx 7 Series FPGAs
par: Kida, Misaki, et autres
Publié: (2025)

Hemlet: A Heterogeneous Compute-in-Memory Chiplet Architecture for Vision Transformers with Group-Level Parallelism
par: Wang, Cong, et autres
Publié: (2025)

Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization
par: Zhu, He, et autres
Publié: (2025)

PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs
par: Malekar, Jinendra, et autres
Publié: (2025)

UVLLM: An Automated Universal RTL Verification Framework using LLMs
par: Hu, Yuchen, et autres
Publié: (2024)

Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference
par: Geens, Robin, et autres
Publié: (2026)

A Tensor-Train Decomposition based Compression of LLMs on Group Vector Systolic Accelerator
par: Huang, Sixiao, et autres
Publié: (2025)

FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs
par: Xie, Xilong, et autres
Publié: (2025)

Modulo-$(2^{2n}+1)$ Arithmetic via Two Parallel n-bit Residue Channels
par: Jaberipur, Ghassem, et autres
Publié: (2024)

Semicustom Frontend VLSI Design and Analysis of a 32-bit Brent-Kung Adder in Cadence Suite
par: Singh, Yashvardhan
Publié: (2025)

WebRISC-V: A 64-bit RISC-V Pipeline Simulator for Computer Architecture Classes
par: Giorgi, Roberto, et autres
Publié: (2025)

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
par: Duan, Bowen, et autres
Publié: (2026)

Hierarchical Source-to-Post-Route QoR Prediction in High-Level Synthesis with GNNs
par: Gao, Mingzhe, et autres
Publié: (2024)

ARAS: An Adaptive Low-Cost ReRAM-Based Accelerator for DNNs
par: Sabri, Mohammad, et autres
Publié: (2024)

VerilogMonkey: Exploring Parallel Scaling for Automated Verilog Code Generation with LLMs
par: Niu, Juxin, et autres
Publié: (2025)

A Survey on LUT-based Deep Neural Networks Implemented in FPGAs
par: Guo, Zeyu
Publié: (2025)

Transitive Array: An Efficient GEMM Accelerator with Result Reuse
par: Guo, Cong, et autres
Publié: (2025)