A pseudo operating system for local and cloud compute (Opensourcing on 5000th star)

CUDA kernels in any language supported by LLVM

Revives the last functional CUDA deep-learning stack on macOS High Sierra. NVIDIA CUDA 10.2 + cuDNN 7.6.5 + PyTorch 1.7.0 fully working on GTX Pascal GPUs — a discontinued ecosystem resurrected.

A ray-tracer/path-tracer implemented in JavaScript using the WebGL 2 API

The .NET wrapper of the Cocaine C library. Cocaine is a multi-platform C library that can be used to accelerate large workloads/big data/anything really with the power of a GPU with ease.

Browser-based Finite Element Analysis solver showcasing WebGPU compute and Rust → WebAssembly numerical pipelines.

.NET binding for wgpu-native

Cocaine is a multi-platform C library that can be used to accelerate large workloads/big data/anything really with the power of a GPU with ease. A .NET wrapper is available in the link below.

Autonomous ML research agent skill (Agent Skills format). Designs experiments, deploys to Modal GPUs, tracks budget, iterates autonomously.

GPU Implementation of Mandelbrot Fractal Generator with Benchmarking

GPU based mean filed/rate theory/cluster dynamic packages for SiChuan university.

Conceptual path finding in high-dimensional embedding space via Grassmann manifold geometry. Replaces cosine similarity with tangent space distance — paths follow domain-coherent lanes instead of converging to vocabulary hubs. GPU-accelerated Julia compute worker

GPU Implementation of Newton Fractal Generator with Benchmarking

Common Lisp minimal GPU code example

🏛️ The Power Economy | Sovereign Infrastructure & BTM AI Assets. Featuring behindthemeterpower.com & behindthemeterai.com. 📧 ceallo6@proton.me

Voxel engine from scratch in Swift + Metal for Apple Silicon

A distributed continuity layer for AI infrastructure

High-performance Mandelbrot fractal explorer using Apple Metal compute shaders. Real-time GPU rendering, smooth coloring, BMP export, and native macOS UI.

ComputeScan analyzes tfplan.json to catch GPU oversizing, autoscaling misconfigurations, tag drift, and high-risk idle patterns. Instantly, offline, and with zero setup. Designed for AI/ML infra teams and fully aligned with the GuardSuite governance engine.

An HLSL implementation of a thread group wide bitonic sort for GPU