Device-wide scan, rivaling NVIDIA CUB.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

NVIDIA GPU Overclocking for Wayland - GTK4/libadwaita

CUDA Core Compute Libraries

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

Rust source code of GPU Governor Core

🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

🚀 Optimize NDCG in neural information retrieval systems using gradient-free techniques with this PyTorch implementation of Evolution Strategies.

📝 Record spans with `tracing-subscriber` for `samply`, using a marker file format for effective runtime profiling. Enhance your tracing capabilities now.

📚 Formalize Kakeya sets in finite fields with Lean 4, establishing lower bounds on their size and advancing mathematical understanding in a structured way.

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

🤖 Streamline AI development with SPEC-AGENTS.md, enabling natural-language interaction and project memory for efficient coding and improved accuracy.

🤖 Enhance your images effortlessly with AI-powered upscaling using Real-ESRGAN in this user-friendly desktop application.

🔧 Generate custom Ethereum vanity addresses quickly and efficiently using Metal GPU acceleration on Apple Silicon.

🔊 Deploy Orpheus TTS with ease using Docker, featuring GPU management, multiple access modes, and optimized performance for production-ready applications.

🧮 Compare the performance of sorting algorithms like QuickSort, MergeSort, and RadixSort with this comprehensive Java implementation and benchmarking tool.

🚀 Optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels using reinforcement learning, surpassing cuBLAS and other benchmarks with superior performance.

🎨 Deploy Ovis-Image effortlessly with a one-click Docker setup for high-quality text-to-image generation, featuring a Web UI and REST API support.

🔍 Optimize your search with TIM, a GPU-accelerated fuzzy search engine that matches patterns in large datasets using advanced wave vector techniques.