Master Quality Authenticated codec reverse engineering, Tool to identify MQA encoding and Master's Sample Rate

Collections of papers, databases, and codes targeted at point cloud quality assessment (PCQA), mesh quality assessment (MQA), 3D model quality assessment (3DQA).

A beautiful Windows program for analyzing audio quality — detects fake lossless, clipping, MQA, and AI-generated audio; includes a spectrogram viewer and more. Built-in player with EQ and spatial audio.

Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.

MHA, MQA, GQA, MLA 相关原理及简要实现

Profile-based three dimensional convolutional neural network for protein model quality assessment

Metadata Quality Stack is a comprehensive toolkit for analysing metadata quality. It implements the European Data Portal's MQA methodology. Docker Compose deployment and React web application.

Reference Flash Attention implementation in PyTorch with V1/V2, GQA/MQA, Triton kernels, benchmark and docs.

Docker Compose for Metadata Quality Assessment (MQA) on CKAN and European Data Portal catalogs

Comprehensive High-Resolution Audio management and streaming application for Android. It transforms your mobile device into a powerful **DLNA/UPnP Media Server**, allowing you to stream your local high-fidelity music collection to any compatible renderer (Hi-Fi streamers, Smart TVs, AV Receivers) or play it locally with audiophile-grade quality.

A code deep-dive on one of the key innovations from Deepseek - Multihead Latent Attention (MLA)

Create a local database of MQA albums from Tidal

Web app for evaluating the quality of RDF metadata based on the EDP's MQA methodology. It supports DCAT-AP, DCAT-AP-ES and NTI-RISP (Spanish DCAT). Built with React and TypeScript. It is easily deployable to GitHub Pages.

Modern LLM Attention from Scratch — MHA, GQA, MQA, RoPE, and KV-Cache implemented in pure PyTorch.

buggy TIDAL Downloader

🚀 Accelerate attention mechanisms with FlashMLA, featuring optimized kernels for DeepSeek models, enhancing performance through sparse and dense attention.

A fast, lightweight cross-os toolkit for detecting, analyzing, organizing, and exporting MQA-encoded FLAC files.

⚡ Optimize attention mechanisms with FlashMLA, a library of advanced sparse and dense kernels for DeepSeek models, improving performance and efficiency.