G

gpu

Zig Vulkan compute library for GPU-accelerated computing. Provides a high-level API for compute shaders, memory management, and kernel execution on Vulkan-capable GPUs.

A comprehensive CUDA compute library for Zig providing GPU memory management, kernel compilation/launching, device probing, and profiling capabilities

Kubernetes device plugin implementing the sharing of Nvidia GPUs between workloads

VanitySearch is a tool designed for finding Bitcoin address prefixes. If you wish to generate a secure private key, please use the -s option to enter your passphrase; this passphrase will be used to generate a base key compliant with the BIP38 standard (e.g., VanitySearch.exe -s "my passphrase" 1MyPrefix). Alternatively, you can use the command VanitySearch.exe -ps "my passphrase", which incorporates an additional cryptographically secure seed into your passphrase. This update addresses bugs related to custom address matching and private key conversion, replaces the random number generator, introduces new search puzzles tailored to specific finite regions, and adds both "random" and "incremental" search modes. Furthermore, the -e option has been added to enable homomorphic properties—a feature that has been completely reimplemented—while the integration of the AVX2 instruction set optimizes CPU performance and enhances underlying logic.

Track AI spending across API providers, MCP tools, subscriptions, and self-hosted GPUs from your terminal. One CLI to see what you're actually paying — Anthropic, OpenAI, OpenRouter, vLLM on your own hardware — with real TCO math. Compare your self-hosted $/MTok vs cloud pricing. Local-first, no SaaS required.

KeyKiller is designed to achieve extreme performance on modern NVIDIA GPUs, solving the Satoshi puzzle. It leverages CUDA, warp-level parallelism, and batched EC operations to push the boundaries of cryptographic key discovery. It is commonly used in research projects such as Secp256k1-CUDA,Brainflayer,BitCrack, Keyhunt CUDA BitCrack,RCKangaroo.

Intel GPU metrics exporter, written in Go

An Efficient Solver for Three and Four Phonon Scattering Rates on Graphics Processing Units

// Project from 2009-2012 // Cross-platform CFD library for mesh-free simulation and visualization of incompressible flows using Smoothed Particle Hydrodynamics (SPH) methods.

A collection of awesome algorithms, implemented in CUDA.