TinyMaix is a tiny inference library for microcontrollers (TinyML).

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

High Performance LLM Inference Operator Library

高性能计算系统性能评价工具集

机械臂+大模型+多模态=人机协作具身智能体

「Octoday Hub 星期八具身智能生态社区」聚合论文、项目、课程、工具、数据集、招聘等资源，连接全球开发者、研究者与产业伙伴。

仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能

[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

基于 11 个内容洞见维度的自媒体创作 Skill，适用于各种智能体 给它一个主题，它给你一篇完整的文章、5 个备选标题、以及每张配图的生成 prompt。

《一人企业方法论》第二版，也适合做其他副业（比如自媒体、电商、数字商品）的非技术人群。

CMSIS-DSP embedded compute library for Cortex-M and Cortex-A

Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

处理器相关文集

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

✨✨Latest Advances on Multimodal Large Language Models

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

how to optimize some algorithm in cuda.

Daily AI ecosystem digest from 10 sources (GitHub, ArXiv, HN, HuggingFace, Product Hunt, Dev.to, Lobste.rs). Bilingual ZH/EN reports via GitHub Actions.

An agentic skills framework & software development methodology that works.

A high-throughput and memory-efficient inference and serving engine for LLMs

Implementation of Diffusion Convolutional Recurrent Neural Network in Tensorflow

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

「C/C++学习+面试指南」一份涵盖大部分 C++ 程序员所需要掌握的知识。入门、进阶、深入、校招、社招，准备 C++ 学习& 面试，首选 CppGuide！

Fast and memory-efficient exact attention

MobileLLM-R1

collection of works aiming at reducing model sizes or the ASIC/FPGA accelerator for machine learning