Cover Image

HiFloat4 Format for Language Model Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Yuanyong, Huang, Jing, Cheng, Yu, Yu, Ziwei, Tang, Kaihua, Ma, Xinda, Wang, Xin, Tong, Anping, Hu, Guipeng, Xu, Yun, Taghian, Mehran, Wu, Peng, Li, Guanglin, Peng, Yunke, Hu, Tianchi, Chen, Minqi, Mi, Michael Bi, Liu, Hu, Zhou, Xiping, Wang, Junsong, Lin, Qiang, Liao, Heng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Hardware Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ascend HiFloat8 Format for Deep Learning
by: Luo, Yuanyong, et al.
Published: (2024)

HiFloat4 Format for Language Model Pre-training on Ascend NPUs
by: Taghian, Mehran, et al.
Published: (2026)

M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization
by: Hu, Weiming, et al.
Published: (2026)

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
by: Zhao, Pengxiang, et al.
Published: (2026)

From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing
by: Zhao, Yushu, et al.
Published: (2025)

A Full-Stack Performance Evaluation Infrastructure for 3D-DRAM-based LLM Accelerators
by: Li, Cong, et al.
Published: (2026)

Apple vs. Oranges: Evaluating the Apple Silicon M-Series SoCs for HPC Performance and Efficiency
by: Hübner, Paul, et al.
Published: (2025)

Fast Cross-Operator Optimization of Attention Dataflow
by: Chang, Haodong, et al.
Published: (2026)

TimeFloats: Train-in-Memory with Time-Domain Floating-Point Scalar Products
by: Hashem, Maeesha Binte, et al.
Published: (2024)

BBAL: A Bidirectional Block Floating Point-Based Quantisation Accelerator for Large Language Models
by: Han, Xiaomeng, et al.
Published: (2025)

HiHGNN: Accelerating HGNNs through Parallelism and Data Reusability Exploitation
by: Xue, Runzhen, et al.
Published: (2023)

FPGA-based Emulation and Device-Side Management for CXL-based Memory Tiering Systems
by: Chen, Yiqi, et al.
Published: (2025)

Closing the Gap Between Float and Posit Hardware Efficiency
by: Jonnalagadda, Aditya Anirudh, et al.
Published: (2026)

BoolE: Exact Symbolic Reasoning via Boolean Equality Saturation
by: Yin, Jiaqi, et al.
Published: (2025)

Timing-driven Approximate Logic Synthesis Based on Double-chase Grey Wolf Optimizer
by: Hu, Xiangfei, et al.
Published: (2024)

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM
by: Yu, Zhongkai, et al.
Published: (2024)

Scaling Laws for Floating Point Quantization Training
by: Sun, Xingwu, et al.
Published: (2025)

Fast Generation of Custom Floating-Point Spatial Filters on FPGAs
by: Campos, Nelson, et al.
Published: (2024)

Online Alignment and Addition in Multi-Term Floating-Point Adders
by: Alexandridis, Kosmas, et al.
Published: (2024)

Floating Point HUB Adder for RISC-V Sargantana Processor
by: Bandera, Gerardo, et al.
Published: (2024)

LLM-Powered Code Analysis and Optimization for Gaussian Splatting Kernels
by: Hu, Yi, et al.
Published: (2025)

QiMeng-CPU-v2: Automated Superscalar Processor Design by Learning Data Dependencies
by: Cheng, Shuyao, et al.
Published: (2025)

TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments
by: Guan, Yue, et al.
Published: (2026)

HiMA: Hierarchical Quantum Microarchitecture for Qubit-Scaling and Quantum Process-Level Parallelism
by: Zhou, Qi, et al.
Published: (2024)

TransDot: An Area-efficient Reconfigurable Floating-Point Unit for Trans-Precision Dot-Product Accumulation for FPGA AI Engines
by: Wang, Jiayi, et al.
Published: (2026)

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

Floating-Point Multiply-Add with Approximate Normalization for Low-Cost Matrix Engines
by: Alexandridis, Kosmas, et al.
Published: (2024)

Converting Binary Floating-Point Numbers to Shortest Decimal Strings: An Experimental Review
by: Gareau, Jaël Champagne, et al.
Published: (2026)

Accelerator-assisted Floating-point ASIP for Communication and Positioning in Massive MIMO Systems
by: Attari, Mohammad, et al.
Published: (2025)

Mixed Structural Choice Operator: Enhancing Technology Mapping with Heterogeneous Representations
by: Hu, Zhang, et al.
Published: (2025)

Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design
by: Yu, Tao, et al.
Published: (2024)

A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training
by: Ali, Sami Ben, et al.
Published: (2024)

Search Your Block Floating Point Scales!
by: Gupta, Tanmaey, et al.
Published: (2026)

AGON: Automated Design Framework for Customizing Processors from ISA Documents
by: Li, Chongxiao, et al.
Published: (2024)

H-FA: A Hybrid Floating-Point and Logarithmic Approach to Hardware Accelerated FlashAttention
by: Alexandridis, Kosmas, et al.
Published: (2025)

MXFormer: A Microscaling Floating-Point Charge-Trap Transistor Compute-in-Memory Transformer Accelerator
by: Karfakis, George, et al.
Published: (2026)

Schrödinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training
by: Nikolić, Miloš, et al.
Published: (2022)

Theseus: Exploring Efficient Wafer-Scale Chip Design for Large Language Models
by: Zhu, Jingchen, et al.
Published: (2024)

AI-Powered Agile Analog Circuit Design and Optimization
by: Hu, Jinhai, et al.
Published: (2025)

A Computing-in-Memory-based One-Class Hyperdimensional Computing Model for Outlier Detection
by: Wang, Ruixuan, et al.
Published: (2023)