在大陆地区使用普通银联信用卡通过 Apple Store 订阅 ChatGPT Plus 等产品的一些实践

Rust macOS automation toolkit — screenshot, OCR, accessibility CLI, break reminder, and more, built on Apple native frameworks via objc2

CUDA/Metal accelerated language model inference

Open-source CUDA compiler targeting multiple GPU architectures. Compiles .cu to AMD and Tenstorrent GPU's

一个跨平台、自动化、全兼容的 Sing-box 一键部署脚本

Local voice input with screen-aware context. Push-to-talk → Whisper → LLM refinement, all on your own GPU.

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Luban: Chart the cosmos of ideas

基于Rust的大模型推理框架

Open-Source Frontier Voice AI

Using mac style hotkeys under Windows

Terminal JSON viewer & processor

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

健康学习到150岁 - 人体系统调优不完全指南

Slide decks, coding exercises, and quick references for learning the JAX AI Stack

The Art of Debugging Open Book

A collection of research papers on low-precision training methods

Simple PyTorch Tutorials Zero to ALL!

Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.

We want to compare how good Qwen3-1.7B-Base using B200 to continue pretraining on Malaysian multi-lingual corpus on different mixed precision training with proper truncated multi-packing.

how to optimize some algorithm in cuda.

implement GPT-OSS 20B & 120B C++ inference from scratch on AMD GPUs

Learn CUDA with PyTorch

tinygrad port of U^2 Net model

Llama 2 Everywhere (L2E)

Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step