Rebeauty Atlas는 무엇인가요?

Rebeauty Atlas는 AI·디자인·마케팅·경제·의료 등 다양한 주제의 Medium 아티클을 수집해 태그·트랙·위키·인사이트로 탐색할 수 있게 정리한 리서치 아카이브입니다.

글은 어떻게 모이나요?

Rebeauty Atlas는 Medium에 공개된 아티클을 자동 수집해 AI·디자인·마케팅·경제·의료 등 주제별 태그·트랙·위키로 정리하는 리서치 아카이브입니다.

사이트는 어떤 섹션으로 구성되어 있나요?

Articles · Wiki · Insights · Tags 섹션으로 구성되어 있으며, PHP MVC · MySQL · shadcn-style UI · Wiki via keyword rules 로 만들어졌습니다.

Articles · Rebeauty Atlas

HUM AI SPT

AS Ashutoshkumarsingh

A Systematic Audit of FP16 Overflow Vulnerabilities in Apple’s coremltools Converter

Every Core ML model running on an iPhone’s Neural Engine operates in fp16 arithmetic. The maximum representable value in fp16 is 65,504…

May 29, 2026 · 4 min read · 2 claps #machine-learning #coreml #apple-neural-engine

AI LIF

VA varun rao · Python in Plain English

Quantization Benchmarks: FP16 vs INT8 vs GPTQ vs AWQ — Which One Matters in Practice?

Or: How I Learned to Stop Worrying and Love Smaller Models

Dec 28, 2025 · 6 min read · 14 claps #quantization #fp16 #llm-serving

Quantization Benchmarks: FP16 vs INT8 vs GPTQ vs AWQ — Which One Matters in Practice?

AI

AL Alain Airom (Ayrom)

Shrinking Giants: A Word on Floating-Point Precision in LLM Domain for Faster, Cheaper Models

Ever wondered how floating-point decision can have an impact on LLM’s output?

Nov 21, 2025 · 8 min read · 5 claps #floating-points #fp4 #fp16

Shrinking Giants: A Word on Floating-Point Precision in LLM Domain for Faster, Cheaper Models

HUM AI

YO YouShin kim

Defeating the Training-Inference Mismatch via FP16** (FP16을 통한 학습-추론 불일치 문제 해결)

### 배경 및 개요

Nov 09, 2025 · 11 min read · 0 claps #llm #reinforcement-learning #fine-tuning

GEN AI SCI

RS Rshravan

PART 3 — MEMORY… IS THE REAL COMPUTE

This is a dramatized version of how things “may have” unfolded, intended to make core math, engineering concepts, and complicated ideas…

Aug 05, 2025 · 6 min read · 50 claps #llm #nvidia #neural-networks

AI

GE Gen. Devin DL.

Introduction to AI Model Quantization Formats

When downloading models on HuggingFace, you often come across model names with labels like FP16, GPTQ, GGML, and more. For those unfamiliar…

Oct 24, 2023 · 4 min read · 38 claps #fp16 #gptq #ggml

Introduction to AI Model Quantization Formats

AI

DA daewoo kim

GPU TensorCore를 최대한 이용하기 위한 Mixed Precision Training

어떻게 training하느냐에 따라 모델의 성능이 달라진다….

Aug 21, 2021 · 4 min read · 6 claps #tensor-core #mixed-precision-training #gpu

GPU TensorCore를 최대한 이용하기 위한 Mixed Precision Training

SPT HUM AI

GR Grigory Sapunov

FP64, FP32, FP16, BFLOAT16, TF32, and other members of the ZOO

There are many floating point formats you can hear about in the context of deep learning. Here is a summary of what are they about and…

May 16, 2020 · 7 min read · 631 claps #deep-learning #floating-points #tf32

FP64, FP32, FP16, BFLOAT16, TF32, and other members of the ZOO

AI TCH

IO Ion Thruster

An Introduction to Writing FP16 code for NVIDIA’s GPUs

The What, Why and How

Dec 22, 2018 · 4 min read · 23 claps #programming #cuda #nvidia