#gpu

GPU-accelerated 2D matrix operations for Go, powered by WebGPU (gogpu/wgpu)

Live per-process CPU / memory / GPU telemetry for a running Slurm job — see whether you're actually using what you requested.

Safe Rust bindings for Apple's Metal framework

Terminal-first GPU fleet manager for deploying, monitoring, and managing vLLM, llama.cpp, and ComfyUI workloads.

An imperative command-line-interface for AI workload orchestration

🦀🌡️ Real-time system monitor for Apple Silicon Macs (M1–M5). No sudo. TUI, JSON/Prometheus metrics server, and Rust library.

No repository description published.

No repository description published.

No repository description published.

Simple profiler scopes for wgpu using timer queries

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Safe Rust wrapper for the NVIDIA Management Library

No repository description published.

An easy tool to monitor the performance of your R3F application.

Exports GPU statistics for Intel Quick Sync Video GPU's

High-performance RDMA for Python and PyTorch (ibverbs, efa, NVMe-oF)

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

webgl implementation for node.js using native-gles

A simple mocker for testing threaded development

Components collection and extensions for Blazor applications.

VDI Stream Client is a very tiny, low latency and GPU accelerated client to connect to Windows running Parsec Host.

Portable Docker + GPU Based Development Environment

The best NVIDIA GPU update checker for Windows power users/gamers. Fully open sourced and lightweight.

Cross platform .NET bindings for Vulkan, VMA, SPIRV-Cross and shaderc

Benchmarking Tool for [GPU.js](https://github.com/gpujs/gpu.js)

GPU texture filter library for wgpu: composable filters, a pure-data filter trait, and a GPU runtime

Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...

Cloud GPU render farm for Blender, for AI agents: MCP server (remote + stdio) and CLI. Render Blender without a GPU from Claude, ChatGPT, Claude Code, Codex, Cursor. Free up to 500 JPY of GPU time per new key, then 0.1 JPY per GPU-second.

SDK for interfacing with Thunder Compute Sandboxes.

A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.