Fast and memory-efficient exact attention

OpenVLA: An open-source vision-language-action model for robotic manipulation.

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Coding problems used in aider's polyglot benchmark

QLoRA: Efficient Finetuning of Quantized LLMs

NVIDIA Inference Xfer Library (NIXL)

Open-Source Frontier Voice AI

Gemini API 中转代理

得到每周一算法

Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"

AI-er难眠之夜

SillyTavern酒馆的长期记忆增强插件

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Roadmap of DL and ML, some courses, study notes and paper summary

Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.

This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025

📚 算法和数据结构教程

Fast and memory-efficient exact attention

Fast Multimodal LLM on Mobile Devices

🔥Unity国际版下载站，可通过直链或者Unity Hub下载例如Unity 6等Unity Editor的国际版，支持添加组件、下载国际版Unity Hub、包含长期支持版、技术支持版、测试版、预览版的Unity。

UniRobot is an embodied intelligent software framework that integrates the robot brain (data, models, model training) with the robot body (perception, model inference, control).

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

All in One Version : Youtube WAV Download, Separating Vocal, Splitting Audio, Training, and Inference Using Google Colab

A WebUI to create song covers with any RVC v2 trained AI voice from YouTube videos or audio files.

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.