CUDA GitHub Repositories (2026) · Open Source Tools

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update.

Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.

A high-throughput and memory-efficient inference and serving engine for LLMs

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

Translate GPU shaders and compute kernels between GLSL, HLSL, Metal, SPIR-V and Slang, from CUDA and HIP, and to WGSL, through the CrossGL IR

Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.17 α).

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twelve Labs, Runway, and Descript.

FlashInfer: Kernel Library for LLM Serving

NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.

SGLang is a high-performance serving framework for large language models and multimodal models.

The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.

AI sovereignty for the world's most trusted runtime.

Speaker diarization in Rust with pyannote-level accuracy. 1790–5970x realtime on NVIDIA GPUs, 430–910x on Apple Silicon.

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.