neo yang nerososft
- Arctic Research Station
- https://synestiaos.github.io
Stars
Compiler for multiple programming models (SYCL, C++ standard parallelism, HIP/CUDA) for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous progra...
Minimalistic C++/Python GUI library for OpenGL, GLES2/3, Metal, and WebAssembly/WebGL
An efficient C++20 GPU numerical computing library with Python-like syntax
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O
A 3D FPGA GPU for real-time rasterization with a tile-based deferred rendering (TBDR) architecture, featuring transform & lighting (T&L), back-face culling, MSAA anti-aliasing, ordered dithering, etc.
炊紙(kashikishi) is a text editor that utilizes GPU to edit text in a 3D space.
Documentation on how to use the Rust Programming Language to develop firmware for bare metal (microcontroller) devices
A Linux-capable RISC-V multicore for and by the world
Makepad is a creative software development platform for Rust that compiles to wasm/webGL, osx/metal, windows/dx11 linux/opengl
A markup-based typesetting system that is powerful and easy to learn.
Elias Daler's Bikeshed Renderer (Vulkan renderer/game engine)
Minimal, configurable & GPU accelerated Immediate Mode UI Library written with modern OpenGL
A deep-dive on the entire history of deep-learning
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型,任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型,单并发20tps;INT4量化模型单并发30tps,多并发可达60+。
Compiler for the COOL language written in C.
A minimal GPU design in Verilog to learn how GPUs work from the ground up
MIT IAP short course: Matrix Calculus for Machine Learning and Beyond
An implementation of a small TCP/IP protocol stack for learning.