Open source repositories tagged with #cuda, ranked by health score.
From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).
NVIDIA GPU Operator creates, configures, and manages GPUs in Kubernetes
LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
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.
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
Large-scale LLM inference engine
Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS. Supports 0.6B and 1.7B models, 9 voices, 10 languages.
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
ONNX Runtime Server: The ONNX Runtime Server is a server that provides TCP and HTTP/HTTPS REST APIs for ONNX inference.
A retargetable MLIR-based machine learning compiler and runtime toolkit.
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
KeepGPU is a simple CLI app that keeps your GPUs running.
Clojure library for CUDA development
Beginner's Guide to reComputer Jetson
