Stars
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。
ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Triton implementation of FlashAttention2 that adds Custom Masks.
A clean and simple template for developing CUDA C++ kernels and testing them in Python/PyTorch 🚀🚀
YouTube Full Text Search - Search all of YouTube from the command line
This computer vision project analyzes tennis match videos using cutting-edge techniques. It employs YOLOv8 for player detection, finetuned YOLO for ball tracking, and ResNet50 for extracting court …
一个简洁优雅的词典翻译 macOS App。开箱即用，支持离线 OCR 识别，支持有道词典，🍎 苹果系统词典，🍎 苹果系统翻译，OpenAI，Gemini，DeepL，Google，Bing，腾讯，百度，阿里，小牛，彩云和火山翻译。A concise and elegant Dictionary and Translator macOS App for looking up words an…
Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
Slides, notes, and materials for the workshop
flash attention tutorial written in python, triton, cuda, cutlass
Tile primitives for speedy kernels
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
PyTorch native quantization for training and inference
The #1 open-source voice interface for desktop, mobile, and ESP32 chips.
A coding agent for open models like Kimi K3 and GLM 5.3
Puzzles for learning Triton
A personal search engine: Create a searchable library from your personal documents, interests, and more!