VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over an OpenAI-compatible API, with per-device tuned defaults and speculative decode gated byte-identical to plain decode. Hosted instance: inference.tiyuvta.ai
A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/Linux with full GPU capability
Pytorch domain library for recommendation systems
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.
High-performance GPU-accelerated signal processing and visualization framework that runs anywhere.
LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Training/Fine-tuning at the speed of light
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
FlashInfer: Kernel Library for LLM Serving
Fused TBQ4 Flash Attention + MTP + Shared Tensors + Qwen35 SWA Hybrid for llama.cpp — 82+ tok/s, lossless 4.25 bpv KV cache, SWA-bounded deep-context decode (w/ long-range recall) on RTX 4090
Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo
cuDF - GPU DataFrame Library
Pure Rust Inference Engine
A retargetable MLIR-based machine learning compiler and runtime toolkit.