Repository Index

FlashMLA: Efficient Multi-head Latent Attention Kernels

TranslatedOpen-source manuscript of 《深入理解 AI Infra：量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments

• accelerator
• ai-infra
• ai-infrastructure
• book

Vector graphics in Go

• path
• vector-graphics
• html-canvas
• opengl

A vector drawing editor for LaTeX (JavaFX).

• latex
• drawing-editor
• pstricks
• pdf

TranslatedBeat-driven sci-fi light-ring visualization. Pure Canvas, single HTML, zero dependencies. Noncommercial use only. RYDER CODE / Ms MAIKEBAIs CAT | Supports Wallpaper Engine animated wallpapers.

• canvas
• generative-art
• html5
• sci-fi

Imgcompress is a self-hosted image processing toolbox that handles compression, format conversion, and AI background removal in a single web interface. It supports over 70 input formats (including PSD, HEIC, and RAW) and can output common formats or generate PDFs, all without sending files to external services.

• imagecompression
• imageoptimizer
• self-hosted
• webtool

HistoClean is a tool for the preprocessing and augmentation of images used in deep learning models. This easy to use application brings together the most popular image processing packages from across the python universe, meaning no more looking at documentation! HistoClean provides real time feedback to augmentations and preprocessing options. This allows users to evaluate their steps before implementation.

• image-processing
• images
• image-analysis
• deep-learning

GS1-128, GS1-DataMatrix, QR Code, EAN and more. Generates PDF, EPS, SVG, PNG images.

• barcode
• datamatrix
• java
• image