Quantized Attention that achieves speedups of 2.1x and 2.7x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

现在各个宽带运营商都有 IPTV 业务，不用安装有线电视就可以高清无卡顿的看电视。 没有开通 iptv 可以使用抓取的直播源地址，复制到电脑、手机、电视网络盒子等设备上看，如果动手能力强也可以自己抓包获取直播源。 注意、注意、注意：食用组播源的设备必须和光猫在同一个网段！

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

Message Passing Neural Networks for Molecule Property Prediction

The swiss army knife of lossless video/audio editing

The Free Software Media System

在线批量导出微信公众号文章，支持阅读量、评论数据的导出，支持内嵌的音视频导出，无需搭建任何环境，可100%还原文章样式，支持私有部署

A feature-rich command-line audio/video downloader

Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.

一个基于 Android 调试 API + 百度地图实现的虚拟定位工具，并且同时实现了一个可以自由移动的摇杆

molfeat - the hub for all your molecular featurizers

A Python package for processing molecules with RDKit in scikit-learn

⚡ Workflow Automation Platform. Orchestrate & Schedule code in any language, run anywhere, 500+ plugins. Alternative to Zapier, Rundeck, Camunda, Airflow...

13th RDKit UGM. 11-13 September in Zurich, Switzerland

Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory

Facilitating the translation of molecular images in chemical reaction mechanisms into computer readable molecular identities

Dashboards and notebooks in a single place. Create powerful and flexible dashboards using code, or build beautiful Notion-like notebooks and share them with your team.

A cheminformatics library written in Rust

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Structured Text Generation

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

Accurate Neural Network Potential on PyTorch

Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

SRCNN to recover a high-resolution image from a low-resolution input

Code accompanying "How I learned to start worrying about prompt formatting".

This is the official code of the MolNexTR

Minimalist ML framework for Rust