Stars
a small build system with a focus on speed
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
Powerful yet simple to use screenshot software 🖥️ 📸
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
A community-maintained Python framework for creating mathematical animations.
PDFCraft is a free, privacy-focused PDF toolkit that runs entirely in your browser. With 90+ professional tools, you can edit, convert, merge, split, and secure your PDF files without ever uploadin…
Ongoing research training transformer models at scale
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
🎵 A cross-platform music player with Jellyfin / Navidrome / Emby media server support, word-by-word lyrics, desktop & taskbar lyrics, cloud music drive, local library management, audio spectrum vis…
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM
A high-throughput and memory-efficient inference and serving engine for LLMs
An easy to use and efficient memory pool allocator written in C++.
BS::thread_pool: a fast, lightweight, modern, and easy-to-use C++17 / C++20 / C++23 thread pool library
A simple C++11 Thread Pool implementation
Event-driven network library for multi-threaded Linux server in C++11
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
You like pytorch? You like micrograd? You love tinygrad! ❤️
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API