This repository provides native TensorFlow execution in backend JavaScript applications under the Node.js runtime, accelerated by the TensorFlow C binary under the hood. It provides the same API as [TensorFlow.js](https://js.tensorflow.org/api/latest/).
Classify GPU's based on their benchmark score in order to provide an adaptive experience.
machinelearn.js extra module to enable tfjs-node-gpu backend
GPU accelerated WebGL backend for TensorFlow.js
WebGPU for node
A Javascript library for running ONNX models on browsers
The luma.gl core Device API
[](https://www.npmjs.com/package/stats-gl) [](https://www.npmjs.com/package/st
KTX 2.0 (.ktx2) parser and serializer.
ONNXRuntime Node.js binding
stable-diffusion.cpp addon for qvac image/video generation
translation addon for qvac
This package adds a GPU accelerated [WebGPU](https://www.w3.org/TR/webgpu/) backend to TensorFlow.js. It currently supports the following models: - BlazeFace - BodyPix - Face landmarks detection - HandPose - MobileNet - PoseDetection - Universal sentence
bert addon for qvac
HTML5 backend for React DnD
i18next-http-backend is a backend layer for i18next using in Node.js, in the browser and for Deno.
Path tracing renderer and utilities for three.js built on top of three-mesh-bvh.
i18next-fs-backend is a backend layer for i18next using in Node.js and for Deno to load translations from the filesystem.
A simple mocker for testing threaded development
API and CLI for compressing images using the ASTC, ETC, ETC2, BCn (DXTn) and BASIS texture compression standard.
GPU Accelerated JavaScript
Use react-devtools outside of the browser
Amazon Cognito Identity Provider JavaScript SDK
Clerk Backend SDK - REST Client for Backend API & JWT verification utilities
Shared CUDA GPU backend for fib-quant and turbo-quant vector quantization (Hadamard rotation kernel, codebook lookup kernel, parity-verified)
GPU-accelerated tile-based compression engine with 32-way parallel decompression
Rust CLI toolkit for niche optimized genomics file processing and target-based variant workflows
Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe.
Governance policy routing for governed compression — codec selection with admissibility classes and degradation receipts
Experimental Rust implementation of the FibQuant radial-angular vector quantization core
Shared codec/profile/shape/eval traits and typed IDs for governed compression experiments
Runtime integration adapter for semantic-memory compression layer — CompressedSearchPath and ExactFallbackAdapter delegates to turbo-quant/fib-quant
Backend code to use egui with wgpu.
Backend code to use egui with wgpu.
Run Stable Diffusion from Ruby. Supports local Python subprocess (SDXL) and remote Modal GPU endpoints (SD 3.5). Handles S3 file transfer, presigned URLs, and automatic backend dispatch.
dama-rb is a 2D game engine that lets you write games in Ruby using a declarative DSL. The engine renders via a Rust/wgpu backend (Metal, Vulkan, DX12, WebGPU), so your game code is pure Ruby while GPU-accelerated graphics run at native speed. Games can run natively or in the browser via ruby.wasm.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.