Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
-
Updated
Oct 3, 2026 - JavaScript
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
🕸️ Import, inline (and minify) GLSL/WGSL/Slang shader files 🔌
Inspection debugger for WebGPU
Real-time neural frame interpolation in the browser: hand-written WGSL runtime on raw WebGPU, 2.9 MB model, 2x-6x any <video> at 3-4 ms per frame. Chrome extension.
A friendly and extendable shader art engine.
webgpu for node.js
SMAA (Enhanced Subpixel Morphological Antialiasing) post-processing for GLSL and WGSL, as ES module strings and as plain shader files. Both are ports of the reference implementation with the same features: luma, color and depth edge detection, predication, and the temporal resolve with reprojection.
WebGPU implementation for the radix sort algorithm as described in the paper "Fast 4-way parallel radix sorting on GPUs"
WebGPU Shading Language grammar for tree-sitter parser
A Generative Art library made in WebGPU
A tiny zero-dependency browser package that extracts dominant color or color palette from an image using WebGPU API with various algorithms
An online WGSL shader editor and compiler.
Simple floating thing WebGPU + WGSL, vanilla flavour.
Display a webcam feed through WebGPU
🧩 Unopinionated WebGPU Abstraction Library ⚙️
To associate your repository with the wgsl topic, visit your repo's landing page and select "manage topics."