High-precision CFP8 solution for edge computing

YoAhorroEnergia Data Infrastructure (YAE) delivers modular data centers, edge data centers, server rack systems, cold/hot aisle containment, EMS, smart PDU, and AC/DC distribution solutions for Africa and Europe.

Enhancing Precision Agriculture Efficiency Through Edge Computing

Our contribution integrates edge computing with WSN for PA, enhancing energy utilization and data aggregation. This approach effectively tackles data redundancy, transmission efficiency, and network

8-bit Transformer Inference and Fine-tuning for Edge

This work conducts an in-depth analysis of Transformer inference and fine-tuning at the edge using two 8-bit floating-point data types: FP8 and 8-bit posit (Posit8).

A 28nm 128TFLOPS/W Computing-In-Memory Engine Supporting

Recent research has extended computing-in-memory (CIM) to floating-point (FP) operations, enabling high-precision computation to handle complex edge tasks such

Benchmarking Edge AI Platforms for High-Performance ML Inference

We highlight the potential of heterogeneous computing solutions for edge AI, where diverse compute units can be strategically leveraged to boost accurate and real-time inference.

Model Quantization: Concepts, Methods, and Why It Matters

Now that you have a basic understanding of what quantization is, you will learn about the quantization algorithm, showing how high-precision values are converted into low-precision

How can using FP16, BF16, or FP8 mixed precision speed up my

Explains how using FP16, BF16, or FP8 mixed precision can speed up model training by increasing computation speed and reducing memory usage.

Floating-point arithmetic for AI inference — hit or miss?

This topic has gained quite some traction lately, so we set out to find out what this development means for efficient inference on edge devices. Specifically, we look at both the hardware considerations for

A Charge-Digital Hybrid Compute-In-Memory Macro with full

A Charge-Digital Hybrid Compute-In-Memory Macro with full precision 8-bit Multiply-Accumulation for Edge Computing Devices Jinwu Chen, Tianzhu Xiong, Xin Si Southeast University, NanJing, China

NPU Selection Guide: INT8/FP8 Quantization for Edge AI

FP8 formats represent a newer reduced-precision approach. Unlike INT8''s fixed-point representation, FP8 maintains floating-point dynamic range advantages while using only 8 bits. FP8

A comprehensive review of Edge Computing empowered smart

The systems part lists real-world deployed systems used to apply edge computing in precision agriculture, while the algorithms part explains simulation-based methods for data